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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *A
    -0.07
     rulers
    -0.06
     configs
    -0.06
    .Password
    -0.06
     свои
    -0.06
    ,output
    -0.06
     phased
    -0.06
    .dds
    -0.06
    .Collection
    -0.06
    _SET
    -0.06
    POSITIVE LOGITS
     openness
    0.07
    싱
    0.07
    ataires
    0.06
    /fonts
    0.06
     discussing
    0.06
     Buen
    0.06
     Vị
    0.06
    spotify
    0.06
    िश
    0.06
     weakening
    0.06
    Act Density 0.076%

    No Known Activations