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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    movement
    -0.07
    642
    -0.07
    622
    -0.07
     algunos
    -0.07
     ấm
    -0.06
     псих
    -0.06
     مقام
    -0.06
    ouce
    -0.06
     документ
    -0.06
    ivement
    -0.06
    POSITIVE LOGITS
     chicas
    0.07
     DateTimeOffset
    0.06
     favicon
    0.06
    .board
    0.06
     Asian
    0.06
     rape
    0.06
     Supervisor
    0.06
     reserved
    0.06
    (properties
    0.06
    (In
    0.06
    Act Density 0.066%

    No Known Activations