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
     сад
    -0.08
    112
    -0.07
     cho
    -0.06
    oque
    -0.06
    porate
    -0.06
    _Ref
    -0.06
     vient
    -0.06
     riders
    -0.06
     composers
    -0.06
     fazla
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.06
     cookies
    0.06
     BrowserAnimationsModule
    0.06
     groß
    0.06
     kvinna
    0.06
    <>();
↵
    0.06
    aepernick
    0.06
    .handler
    0.06
    ,)↵
    0.06
     mechanism
    0.06
    Act Density 0.032%

    No Known Activations