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

    Neuronpedia

    INDEX
    Explanations

    shear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispon
    -0.07
     president
    -0.07
    ppo
    -0.07
    BoundingBox
    -0.07
     Expo
    -0.07
    _object
    -0.07
     not
    -0.07
    mol
    -0.06
    かけ
    -0.06
    力还是
    -0.06
    POSITIVE LOGITS
     hacks
    0.10
     إدارة
    0.08
    🎨
    0.07
    semantic
    0.07
    קלא
    0.07
    .smtp
    0.07
    _framework
    0.07
    shade
    0.07
     THREAD
    0.07
    antha
    0.07
    Act Density 0.003%

    No Known Activations