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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ---------
    -0.07
     careful
    -0.07
    _SO
    -0.07
    (hist
    -0.06
    έ
    -0.06
    _font
    -0.06
    _TRACK
    -0.06
    本当
    -0.06
    _av
    -0.06
     finalized
    -0.06
    POSITIVE LOGITS
    National
    0.07
    conomics
    0.07
    AMB
    0.07
    nuts
    0.07
    默
    0.06
     motivations
    0.06
     ис
    0.06
     были
    0.06
    ">'.
    0.06
     glor
    0.06
    Act Density 0.008%

    No Known Activations