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

    Neuronpedia

    INDEX
    Explanations

    software installation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vars
    -0.07
    発
    -0.07
    *c
    -0.06
    pered
    -0.06
     endereco
    -0.06
    Difficulty
    -0.06
    $value
    -0.06
     FUNCTIONS
    -0.06
    Arr
    -0.06
    /k
    -0.06
    POSITIVE LOGITS
    >This
    0.07
     İh
    0.07
    icity
    0.07
    /plain
    0.06
     Telescope
    0.06
     mysl
    0.06
    _ssl
    0.06
     anime
    0.06
    imated
    0.06
     сто
    0.06
    Act Density 0.031%

    No Known Activations