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

    Neuronpedia

    INDEX
    Explanations

    star symbols and specific technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     горо
    0.48
     Aguilera
    0.48
     Mysore
    0.46
     Almeida
    0.46
    qttr
    0.45
     Yel
    0.44
     Vries
    0.44
     Lille
    0.44
     IQR
    0.44
     Toro
    0.44
    POSITIVE LOGITS
    レイ
    0.47
    それ
    0.46
     identification
    0.44
     metaphysical
    0.44
    كَ
    0.44
     safari
    0.41
    로
    0.41
     implementation
    0.41
     spelling
    0.41
    define
    0.40
    Act Density 0.002%

    No Known Activations