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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oden
    -0.07
    (io
    -0.07
     DIR
    -0.07
     sausage
    -0.07
     princ
    -0.07
     dialect
    -0.06
    constant
    -0.06
     Müz
    -0.06
    ály
    -0.06
     abstract
    -0.06
    POSITIVE LOGITS
    _pb
    0.07
    _vm
    0.06
    ("\
    0.06
     المغرب
    0.06
    olik
    0.06
    也不
    0.06
    领
    0.06
    猫
    0.06
     appellant
    0.06
     أمريكي
    0.06
    Act Density 0.036%

    No Known Activations