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

    Neuronpedia

    INDEX
    Explanations

    references to individual experiences and perspectives in a narrative context

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

    explaining results or causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     senare
    -0.38
     Offisielt
    -0.35
     Kesehatan
    -0.33
     hagas
    -0.32
     quoque
    -0.32
     possibilités
    -0.31
     eventually
    -0.31
     légales
    -0.30
     later
    -0.30
     medel
    -0.30
    POSITIVE LOGITS
     الحره
    0.62
     CreateTagHelper
    0.58
    0.55
    InitVars
    0.55
     verſch
    0.54
    arakhand
    0.53
    ſicht
    0.53
     Signalez
    0.53
     ſchon
    0.52
    ſehen
    0.52
    Act Density 0.049%

    No Known Activations