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

    Neuronpedia

    INDEX
    Explanations

    autocomplete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fixed
    -0.06
     Faker
    -0.06
     soaked
    -0.06
     beer
    -0.06
     Plane
    -0.06
    VECTOR
    -0.06
    .pkl
    -0.06
     implementations
    -0.06
    push
    -0.06
     Arn
    -0.06
    POSITIVE LOGITS
    autocomplete
    0.08
     autocomplete
    0.07
    ним
    0.07
    aged
    0.07
    >>();↵
    0.06
    age
    0.06
     charg
    0.06
    لال
    0.06
    geb
    0.06
    	select
    0.06
    Act Density 0.003%

    No Known Activations