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

    Neuronpedia

    INDEX
    Explanations

    Steps in time/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vitre
    -0.08
     Grind
    -0.07
     forensic
    -0.07
    ूड
    -0.07
    flug
    -0.07
    .pull
    -0.07
    .draw
    -0.07
     Pull
    -0.07
     napr
    -0.07
     pracov
    -0.07
    POSITIVE LOGITS
    -switch
    0.13
     Switch
    0.11
     переключ
    0.11
     менять
    0.11
     Switching
    0.11
    _switch
    0.11
     switching
    0.10
     switch
    0.10
    Switch
    0.10
    Switcher
    0.10
    Act Density 0.017%

    No Known Activations