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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dep
    -0.07
    .PropertyType
    -0.07
     Fab
    -0.07
    🅦
    -0.07
    葰
    -0.06
    섯
    -0.06
    משפחת
    -0.06
     Philip
    -0.06
    👃
    -0.06
     Horton
    -0.06
    POSITIVE LOGITS
     lanes
    0.07
    Camera
    0.07
    _EPS
    0.07
    ako
    0.07
    _COUNTER
    0.07
     drivers
    0.07
    lí
    0.07
    .points
    0.07
    _running
    0.07
    olidays
    0.06
    Act Density 0.009%

    No Known Activations