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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _chart
    -0.06
    vault
    -0.06
     Raid
    -0.06
     мног
    -0.06
    meter
    -0.06
    Cascade
    -0.06
    CASCADE
    -0.06
     Low
    -0.06
    ordan
    -0.06
     electoral
    -0.06
    POSITIVE LOGITS
     ::↵
    0.06
    .Properties
    0.06
     documenting
    0.06
    문
    0.06
     必
    0.06
    pecial
    0.06
     FILES
    0.06
     transported
    0.06
    ocumented
    0.06
    。那
    0.06
    Act Density 0.032%

    No Known Activations