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

    Neuronpedia

    INDEX
    Explanations

    relates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ValidationError
    -0.07
    谴责
    -0.07
    placement
    -0.07
    Nhap
    -0.06
    Lint
    -0.06
    تنسيق
    -0.06
     Cp
    -0.06
     divisor
    -0.06
    defaultValue
    -0.06
     downtown
    -0.06
    POSITIVE LOGITS
    까요
    0.07
    水晶
    0.07
     Weiss
    0.07
    疏通
    0.07
     countert
    0.07
     outbound
    0.07
     Bubble
    0.06
    effects
    0.06
    您可以
    0.06
     wizards
    0.06
    Act Density 0.003%

    No Known Activations