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

    Neuronpedia

    INDEX
    Explanations

    alumni

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дог
    -0.07
    .PORT
    -0.06
     apk
    -0.06
    "They
    -0.06
     쉽
    -0.06
    靠近
    -0.06
     ganz
    -0.06
    "net
    -0.06
     drm
    -0.06
    报案
    -0.06
    POSITIVE LOGITS
     Salisbury
    0.07
    椟
    0.07
    中午
    0.07
     mín
    0.06
     bakery
    0.06
     �
    0.06
    ф
    0.06
    笄
    0.06
     искусств
    0.06
    ставлен
    0.06
    Act Density 0.002%

    No Known Activations