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

    Neuronpedia

    INDEX
    Explanations

    categories and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    飼
    0.45
    claims
    0.43
    posites
    0.43
     cuadr
    0.42
     এখান
    0.42
    ).-
    0.42
     হাব
    0.41
     এরপর
    0.41
     buradan
    0.41
    XXXX
    0.40
    POSITIVE LOGITS
     catholique
    0.49
    erebbe
    0.44
     entusias
    0.43
    መስ
    0.42
     جدید
    0.42
     स्वप्
    0.42
    CANCEL
    0.42
     grassland
    0.40
    seamless
    0.40
     உருவாக
    0.40
    Act Density 0.001%

    No Known Activations