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

    Neuronpedia

    INDEX
    Explanations

    seeing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     cloves
    -0.06
    _sym
    -0.06
    忘
    -0.06
    itudes
    -0.06
     prolet
    -0.05
    (wait
    -0.05
    ('${
    -0.05
    吐
    -0.05
     phê
    -0.05
    POSITIVE LOGITS
     QQ
    0.07
    [],↵
    0.07
    ğü
    0.06
    ertainment
    0.06
    ***/↵
    0.06
     ZX
    0.06
    ी।↵
    0.06
    _bug
    0.06
     FAQ
    0.06
    ]/
    0.06
    Act Density 0.028%

    No Known Activations