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

    Neuronpedia

    INDEX
    Explanations

    /**

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nails
    -0.07
     chairs
    -0.07
     Ingram
    -0.07
    Advertisement
    -0.07
     Water
    -0.06
    -0.06
     basement
    -0.06
    -0.06
    acciones
    -0.06
    lect
    -0.06
    POSITIVE LOGITS
     �
    0.08
     병
    0.07
     responseObject
    0.07
     Nhất
    0.06
    vyšší
    0.06
    /**
    0.06
    IllegalArgumentException
    0.06
     韓
    0.06
     birlik
    0.06
    ैश
    0.06
    Act Density 0.002%

    No Known Activations