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

    Neuronpedia

    INDEX
    Explanations

    answering/clarifying questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "}}↵
    -0.07
    Control
    -0.06
     přízn
    -0.06
    Good
    -0.06
     harms
    -0.06
    ROLS
    -0.06
     progresses
    -0.06
    t
    -0.06
    ЎыџNЎыџN
    -0.06
    ba
    -0.06
    POSITIVE LOGITS
    ijd
    0.06
    _feed
    0.06
    .sessions
    0.06
     Kelly
    0.06
    _RELEASE
    0.06
    .characters
    0.06
     encount
    0.06
     QVariant
    0.06
    _GAME
    0.05
     fak
    0.05
    Act Density 0.007%

    No Known Activations