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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concealed
    -0.07
    ئت
    -0.07
     Bison
    -0.07
     ""}↵
    -0.07
    шед
    -0.06
    ]));
    -0.06
    BX
    -0.06
     infectious
    -0.06
    ;%
    -0.06
    thesis
    -0.06
    POSITIVE LOGITS
    receiver
    0.07
    /method
    0.07
     anthrop
    0.07
    irector
    0.07
     yeti
    0.07
    武侠
    0.07
     أغسط
    0.07
     Utf
    0.07
    —who
    0.07
     السنوات
    0.07
    Act Density 0.003%

    No Known Activations