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

    Neuronpedia

    INDEX
    Explanations

    inverse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     La
    -0.07
    óng
    -0.07
    Scale
    -0.07
    alpha
    -0.06
     configuration
    -0.06
     SUS
    -0.06
    amax
    -0.06
    	UInt
    -0.06
     сест
    -0.06
    ////////////////////////////////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
    .Apis
    0.07
    .backgroundColor
    0.06
    .connector
    0.06
    0.06
     شما
    0.06
    ервые
    0.06
    _handle
    0.06
    arb
    0.06
     Nüfus
    0.06
     insan
    0.06
    Act Density 0.005%

    No Known Activations