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

    Neuronpedia

    INDEX
    Explanations

    code, files, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nurses
    -0.06
     perpetr
    -0.06
     modulus
    -0.06
     확
    -0.06
     자료
    -0.06
     paranoid
    -0.06
    draw
    -0.06
    _proj
    -0.06
    ssize
    -0.06
     *(
    -0.06
    POSITIVE LOGITS
     мир
    0.08
    hattan
    0.07
     Fond
    0.07
    алів
    0.06
    utenant
    0.06
    _dark
    0.06
    OPLE
    0.06
    ै.↵
    0.06
    _PIPE
    0.06
    BOOLE
    0.06
    Act Density 0.003%

    No Known Activations