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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ETA
    -0.07
    א
    -0.06
     Peng
    -0.06
    این
    -0.06
    .RemoveEmptyEntries
    -0.06
     agitation
    -0.06
    _logs
    -0.06
    etten
    -0.06
    -0.06
     POT
    -0.06
    POSITIVE LOGITS
    lier
    0.06
     ceiling
    0.06
    ierrez
    0.06
     enzyme
    0.06
     entertained
    0.06
     indifferent
    0.06
    .activation
    0.06
    WithURL
    0.06
     The
    0.06
    (order
    0.06
    Act Density 0.000%

    No Known Activations