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

    Neuronpedia

    INDEX
    Explanations

    Evaluation metrics/standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kaç
    -0.07
     그림
    -0.06
    _figure
    -0.06
    REE
    -0.06
     car
    -0.06
    _pick
    -0.06
    нул
    -0.06
    \Component
    -0.06
     shri
    -0.06
     RESULT
    -0.06
    POSITIVE LOGITS
     sending
    0.07
     conject
    0.07
     �
    0.06
    swagen
    0.06
     <+
    0.06
     perfil
    0.06
     разд
    0.06
    υπ
    0.06
     dolayı
    0.06
    leading
    0.06
    Act Density 0.001%

    No Known Activations