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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TZ
    -0.06
    World
    -0.06
    _DEFINITION
    -0.06
     GTA
    -0.06
     اسلامی
    -0.06
     остан
    -0.06
    qus
    -0.06
    Lu
    -0.06
     convened
    -0.06
     Couch
    -0.06
    POSITIVE LOGITS
     Robert
    0.07
     tarihli
    0.06
     Enter
    0.06
     Get
    0.06
     yaklaşık
    0.06
    []=$
    0.06
     brother
    0.06
     unit
    0.06
    いで
    0.06
     Block
    0.06
    Act Density 0.000%

    No Known Activations