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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creativity
    -0.07
     Needs
    -0.07
     Olomou
    -0.07
     Mathematics
    -0.06
     unimagin
    -0.06
     just
    -0.06
     našich
    -0.06
     propName
    -0.06
    Cli
    -0.06
     DK
    -0.06
    POSITIVE LOGITS
    (bool
    0.06
    ($(".
    0.06
    ?>/
    0.06
    getType
    0.06
     tightly
    0.06
    Los
    0.06
    _dirty
    0.06
     sigue
    0.06
    _TRUE
    0.06
    stk
    0.06
    Act Density 0.045%

    No Known Activations