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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _filtered
    -0.07
     Wolver
    -0.06
     healing
    -0.06
    _IMPL
    -0.06
     Олександ
    -0.06
    owe
    -0.06
     drum
    -0.06
    abad
    -0.06
     stomach
    -0.06
    okrat
    -0.06
    POSITIVE LOGITS
    SCALE
    0.07
    (fun
    0.07
    (goal
    0.06
    ([$
    0.06
     Height
    0.06
     SERIAL
    0.06
    	bool
    0.06
    filled
    0.06
    multiply
    0.06
    .removeAll
    0.06
    Act Density 0.001%

    No Known Activations