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

    Neuronpedia

    INDEX
    Explanations

    code followed by numbers or programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upto
    0.55
     till
    0.46
    iyat
    0.44
     gamanam
    0.44
     nochmal
    0.43
     mattresses
    0.43
     Imam
    0.42
     tinh
    0.42
     rumoured
    0.40
     equipments
    0.40
    POSITIVE LOGITS
    Winter
    0.41
    广东
    0.39
    Java
    0.39
    絬
    0.38
    Metall
    0.38
    Elect
    0.37
    ricia
    0.37
    Summer
    0.37
    Conte
    0.37
    getNode
    0.37
    Act Density 0.000%

    No Known Activations