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

    Neuronpedia

    INDEX
    Explanations

    closing tags in template syntax, specifically related to code structures

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

    user input followed by code or math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.39
     himself
    -0.37
    xsi
    -0.34
     jopa
    -0.34
     itself
    -0.33
     contemporánea
    -0.32
     mármol
    -0.32
     aberta
    -0.31
     desnuda
    -0.31
     even
    -0.30
    POSITIVE LOGITS
    sequence
    1.09
     sequence
    0.77
     propOrder
    0.74
    sequences
    0.69
     resourceCulture
    0.66
     sequences
    0.63
    sequ
    0.63
     Sequences
    0.60
     sequencing
    0.60
     Sequence
    0.59
    Act Density 0.001%

    No Known Activations