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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    survey
    -0.08
    	usage
    -0.07
    @Service
    -0.07
    继
    -0.06
    .Highlight
    -0.06
     завдання
    -0.06
    Mut
    -0.06
    .Act
    -0.06
    .sat
    -0.06
     suitability
    -0.06
    POSITIVE LOGITS
    askan
    0.07
     checkout
    0.07
    idar
    0.07
     chin
    0.06
    oped
    0.06
     druhé
    0.06
    _pd
    0.06
    _EP
    0.06
     stav
    0.06
    ège
    0.06
    Act Density 0.000%

    No Known Activations