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

    Neuronpedia

    INDEX
    Explanations

    Creating and designing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.52
     salir
    0.48
    MN
    0.47
    al
    0.46
    Mn
    0.45
    iniu
    0.45
     bushing
    0.45
    LN
    0.45
    G
    0.44
     A
    0.44
    POSITIVE LOGITS
     assaults
    0.42
    ження
    0.41
    炤
    0.41
    દા
    0.41
    ጨማሪ
    0.41
    proba
    0.40
    Conn
    0.40
    禣
    0.40
    वण्यासाठी
    0.39
    ୍କ
    0.39
    Act Density 0.002%

    No Known Activations