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

    Neuronpedia

    INDEX
    Explanations

    ub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surg
    -0.07
     gaps
    -0.06
     Layer
    -0.06
     Afrika
    -0.06
    ValidationError
    -0.06
     neighbor
    -0.06
     риз
    -0.06
     pazar
    -0.06
     (&
    -0.06
     Zap
    -0.06
    POSITIVE LOGITS
     cub
    0.07
    ）。↵
    0.07
     grate
    0.07
    _Bool
    0.06
    AGES
    0.06
    ธาน
    0.06
    동안
    0.06
     Categoria
    0.06
    memberof
    0.06
    .INVALID
    0.06
    Act Density 0.001%

    No Known Activations