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

    Neuronpedia

    INDEX
    Explanations

    statements expressing levels of agreement or consensus in scientific discourse

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

    in good agreement with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnitId
    -0.38
     kids
    -0.35
    setattr
    -0.35
     barriers
    -0.33
     PPS
    -0.32
    ┈┈
    -0.31
     estekak
    -0.31
     gates
    -0.31
     Inst
    -0.31
    ATU
    -0.30
    POSITIVE LOGITS
    haikusbot
    0.69
     corroborated
    0.65
     agrees
    0.63
     coincide
    0.62
     agree
    0.60
     agreed
    0.59
     corrobor
    0.59
     concurred
    0.59
     coincides
    0.59
    Tikang
    0.58
    Act Density 0.129%

    No Known Activations