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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cort
    -0.07
    時の
    -0.07
    .ball
    -0.06
     vampire
    -0.06
     ol
    -0.06
    ']=='
    -0.06
    slider
    -0.06
    izr
    -0.06
    -first
    -0.06
     tes
    -0.06
    POSITIVE LOGITS
    ecake
    0.08
    modx
    0.07
    —he
    0.06
     inher
    0.06
    opoly
    0.06
     Genç
    0.06
    captcha
    0.06
    arranty
    0.06
    emacs
    0.06
    kB
    0.06
    Act Density 0.003%

    No Known Activations