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

    Neuronpedia

    INDEX
    Explanations

    to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metų
    0.42
     slippers
    0.40
    वड
    0.39
    ियोग्राफी
    0.39
    鋤
    0.39
     sisters
    0.38
     Cz
    0.37
    椽
    0.36
    CCIÓN
    0.36
    齙
    0.36
    POSITIVE LOGITS
     Synod
    0.37
    喑
    0.37
     assure
    0.35
     sle
    0.35
    topLeft
    0.35
    Repr
    0.35
    ავს
    0.33
    െന്നും
    0.32
    คุณภาพ
    0.32
    窨
    0.32
    Act Density 0.002%

    No Known Activations