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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ализа
    -0.07
    альном
    -0.07
     áreas
    -0.07
    ags
    -0.06
    .vec
    -0.06
     خ
    -0.06
     Documentation
    -0.06
     �
    -0.06
     Kare
    -0.06
     Nil
    -0.06
    POSITIVE LOGITS
    surname
    0.07
    134
    0.06
     Ağustos
    0.06
    ourke
    0.06
     köln
    0.06
     wifi
    0.06
    -cmpr
    0.06
    Library
    0.06
    ←
    0.06
    _pub
    0.06
    Act Density 0.018%

    No Known Activations