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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुमत
    -0.08
     　　　　
    -0.07
    .complete
    -0.07
     탈
    -0.06
    _argument
    -0.06
     Rotate
    -0.06
     opponents
    -0.06
     America
    -0.06
    Move
    -0.06
     Resource
    -0.06
    POSITIVE LOGITS
    ่อไป
    0.06
    ست
    0.06
     韓
    0.06
    omnia
    0.06
    .asInstanceOf
    0.06
    ?,
    0.06
     صند
    0.06
    summary
    0.06
    σιμοποι
    0.05
     homelessness
    0.05
    Act Density 0.025%

    No Known Activations