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

    Neuronpedia

    INDEX
    Explanations

    holiday meals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fusion
    -0.07
     oo
    -0.07
     Reverse
    -0.07
    iras
    -0.06
     (...)
    -0.06
    页面
    -0.06
     Frog
    -0.06
     cylindrical
    -0.06
    аст
    -0.06
     McGill
    -0.06
    POSITIVE LOGITS
    แส
    0.06
    .lua
    0.06
    Published
    0.06
     医
    0.06
     京
    0.06
     Chance
    0.06
    ）:
    0.06
     Defaults
    0.05
    _https
    0.05
     قرارد
    0.05
    Act Density 0.022%

    No Known Activations