Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical expressions and rearrangements

    np_acts-logits-general · gemini-2.0-flash

    rearranging and factoring mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.76
    KURZBESCHREIBUNG
    -0.67
     saites
    -0.59
    رشف
    -0.59
    Trama
    -0.57
    ensin
    -0.56
    GEBURTSDATUM
    -0.56
     CreateTagHelper
    -0.53
    ఔ
    -0.52
    عداد
    -0.52
    POSITIVE LOGITS
     rearrange
    0.67
     rewriting
    0.66
     factoring
    0.66
     שוליים
    0.63
     rewrite
    0.63
     rearrangement
    0.63
     Rear
    0.60
    fact
    0.58
     rearranging
    0.58
     Isol
    0.57
    Act Density 1.038%

    No Known Activations