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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     платеж
    -0.06
    Improved
    -0.06
    _busy
    -0.06
    ucking
    -0.06
    ipy
    -0.06
    OLTIP
    -0.05
    ฟอร
    -0.05
    ับปร
    -0.05
    ((__
    -0.05
     YYS
    -0.05
    POSITIVE LOGITS
    sembl
    0.07
    .recipe
    0.07
     Pas
    0.06
    ून
    0.06
    黒
    0.06
     Cavs
    0.06
     ]↵↵↵
    0.06
    /cart
    0.06
    >)
    0.06
    .count
    0.06
    Act Density 0.986%

    No Known Activations