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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psychiatrist
    -0.07
     substantive
    -0.07
     psychologist
    -0.06
    .translate
    -0.06
     compound
    -0.06
    “We
    -0.06
     ATTACK
    -0.06
    anga
    -0.06
     chains
    -0.06
     Temper
    -0.06
    POSITIVE LOGITS
    尊
    0.07
    天堂
    0.06
    _ALLOWED
    0.06
    -testid
    0.06
    lags
    0.06
    GraphNode
    0.06
    _TYP
    0.06
     ctype
    0.06
     Staten
    0.06
     Bedford
    0.06
    Act Density 0.033%

    No Known Activations