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

    Neuronpedia

    INDEX
    Explanations

    definition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corps
    -0.08
     ran
    -0.07
    (z
    -0.07
     :'
    -0.07
    Scaler
    -0.07
    刻
    -0.07
    (Z
    -0.07
     party
    -0.07
     Share
    -0.06
     ngu
    -0.06
    POSITIVE LOGITS
     definition
    0.14
     definitions
    0.10
    Definition
    0.10
     Definition
    0.09
    definition
    0.08
    inition
    0.08
     midpoint
    0.07
     инструк
    0.07
    ılan
    0.07
    incorrect
    0.07
    Act Density 0.010%

    No Known Activations