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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frozen
    -0.08
    �
    -0.07
    uzzle
    -0.07
     logged
    -0.07
    햑
    -0.06
    toBe
    -0.06
     heaven
    -0.06
    .canvas
    -0.06
    /close
    -0.06
    _Enter
    -0.06
    POSITIVE LOGITS
    objective
    0.07
     ``
    0.07
    ONDON
    0.07
    .How
    0.07
    sil
    0.06
    —not
    0.06
    ('{{
    0.06
     agents
    0.06
    атегор
    0.06
    .Other
    0.06
    Act Density 0.001%

    No Known Activations