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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lb
    -0.06
    UpperCase
    -0.06
    Steps
    -0.05
    spy
    -0.05
    Boston
    -0.05
     surpass
    -0.05
     stint
    -0.05
    frog
    -0.05
    以下
    -0.05
     хоч
    -0.05
    POSITIVE LOGITS
    .keep
    0.07
    _HIDDEN
    0.07
    'es
    0.07
    /check
    0.06
    RowAnimation
    0.06
    /GL
    0.06
    _ASC
    0.06
    .iterator
    0.06
    ＞
    0.06
    /power
    0.06
    Act Density 0.039%

    No Known Activations