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

    Neuronpedia

    INDEX
    Explanations

    recurring events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hayden
    -0.06
    reen
    -0.06
     traffic
    -0.06
     credential
    -0.06
     цих
    -0.06
     Genç
    -0.06
    clazz
    -0.06
    ilor
    -0.05
    high
    -0.05
     teammate
    -0.05
    POSITIVE LOGITS
     icy
    0.06
     aisle
    0.06
     прис
    0.06
     neby
    0.06
    การส
    0.06
    urred
    0.06
    kit
    0.06
    ('/:
    0.06
     fourteen
    0.06
    edik
    0.06
    Act Density 0.257%

    No Known Activations