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

    Neuronpedia

    INDEX
    Explanations

    stability and consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    occ
    -0.07
    рі
    -0.07
    came
    -0.07
    Updating
    -0.07
    .Remote
    -0.06
    (pattern
    -0.06
     Francisco
    -0.06
    aco
    -0.06
    temperature
    -0.06
     Ago
    -0.06
    POSITIVE LOGITS
    同步
    0.08
    numerusform
    0.06
    將
    0.06
     guarding
    0.06
    錢
    0.06
    ']}}</
    0.06
     Fahr
    0.06
    GraphQL
    0.06
    GLuint
    0.06
    �
    0.06
    Act Density 0.094%

    No Known Activations