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

    Neuronpedia

    INDEX
    Explanations

    multiple steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Powerful
    0.45
    Diamonds
    0.38
    cèle
    0.37
    Powerful
    0.37
    방송
    0.36
    itorios
    0.36
    Businessman
    0.35
    AppCompatTheme
    0.35
     DOL
    0.35
    Pray
    0.34
    POSITIVE LOGITS
     ಕಾಣ
    0.43
     elevator
    0.40
    ♓
    0.36
     कॉम
    0.35
    ྡ
    0.35
     swap
    0.35
    גד
    0.35
     посмотреть
    0.34
     asign
    0.34
     invertir
    0.34
    Act Density 0.000%

    No Known Activations