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

    Neuronpedia

    INDEX
    Explanations

    references to variable names and function calls in programming code

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

    Code, variables, or properties

    np_acts-logits-general · gemini-2.0-flash

    programming code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    -0.56
     (
    -0.54
     Ver
    -0.52
     ban
    -0.50
     ver
    -0.49
     del
    -0.49
     
    -0.48
     "
    -0.48
     he
    -0.47
     N
    -0.47
    POSITIVE LOGITS
     poffible
    1.03
    SourceChecksum
    1.02
    Tikang
    1.00
     myſelf
    0.99
    ſelves
    0.94
     Efq
    0.94
     ་་
    0.93
     fevere
    0.93
     defaultstate
    0.92
     purpoſe
    0.92
    Act Density 0.145%

    No Known Activations