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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unw
    -0.07
    /custom
    -0.06
     �
    -0.06
    孤
    -0.06
     الأد
    -0.06
    ۲۷
    -0.06
     amnesty
    -0.06
     поступ
    -0.06
     ημέ
    -0.06
     maduras
    -0.06
    POSITIVE LOGITS
     Professor
    0.08
     drops
    0.07
    cmc
    0.07
    894
    0.07
     caption
    0.07
     elasticity
    0.07
     hinges
    0.06
     comparing
    0.06
     (%
    0.06
     pairs
    0.06
    Act Density 0.000%

    No Known Activations