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
    ゅ
    -0.07
    ḯ
    -0.06
    warf
    -0.06
    cmp
    -0.06
    痄
    -0.06
    Mathf
    -0.06
    hl
    -0.06
    night
    -0.06
    arton
    -0.06
    StringUtil
    -0.06
    POSITIVE LOGITS
     små
    0.07
    ('_
    0.07
     предложения
    0.07
    ToolBar
    0.07
     losses
    0.07
    宏伟
    0.07
    仍未
    0.07
     acquisition
    0.07
     exposures
    0.06
     Casual
    0.06
    Act Density 0.001%

    No Known Activations