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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _io
    -0.07
     associated
    -0.06
     Feast
    -0.06
    Radio
    -0.06
     ability
    -0.06
     PIC
    -0.06
    руется
    -0.06
     StringComparison
    -0.06
     dirname
    -0.06
     dying
    -0.06
    POSITIVE LOGITS
    uell
    0.07
    ')).
    0.06
    "));↵↵
    0.06
    _GU
    0.06
     superf
    0.06
    .reverse
    0.06
    '))↵
    0.06
    met
    0.06
    �
    0.06
    \"");↵
    0.06
    Act Density 0.067%

    No Known Activations