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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uptools
    -0.09
     Skinny
    -0.08
     débat
    -0.08
    ɵ
    -0.08
     matchmaking
    -0.08
     incontournable
    -0.08
     Jupiter
    -0.08
    оград
    -0.08
    .Matchers
    -0.08
     errado
    -0.08
    POSITIVE LOGITS
     medications
    0.11
    是否
    0.10
     hobbies
    0.10
     history
    0.09
     antecedentes
    0.09
     allergies
    0.09
     surgeries
    0.09
    有没有
    0.09
     diary
    0.09
     medicamentos
    0.09
    Act Density 0.013%

    No Known Activations