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

    Neuronpedia

    INDEX
    Explanations

    awful, awake, awakening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.63
     It
    1.43
     \
    1.42
     i
    1.39
    -
    1.39
     &
    1.34
     Have
    1.34
     have
    1.33
     In
    1.31
    d
    1.27
    POSITIVE LOGITS
    न
    1.40
    ＮＡＮＡ
    1.34
     powied
    1.34
    νει
    1.27
     밝혔
    1.22
    ವಲ್ಲ
    1.22
    스
    1.22
     sympathique
    1.21
    ة
    1.21
    ನ
    1.20
    Act Density 0.000%

    No Known Activations