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

    Neuronpedia

    INDEX
    Explanations

    ness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Console
    -0.06
    üfus
    -0.06
    緊
    -0.06
    (score
    -0.06
    gan
    -0.06
     мир
    -0.06
    stalk
    -0.06
    して
    -0.06
     pasado
    -0.06
    さま
    -0.06
    POSITIVE LOGITS
    letal
    0.07
     promptly
    0.06
    ruit
    0.06
     norms
    0.06
     Extremely
    0.06
     clinics
    0.06
    Including
    0.06
    OLS
    0.06
     paraph
    0.06
    stdint
    0.06
    Act Density 0.003%

    No Known Activations