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

    Neuronpedia

    INDEX
    Explanations

    text fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zagre
    0.40
    গায়
    0.38
    が無い
    0.38
     Киев
    0.37
     nggak
    0.37
    }}}=\
    0.36
     बड़ी
    0.36
     الاكس
    0.36
     Donne
    0.35
    Cox
    0.35
    POSITIVE LOGITS
     LZ
    0.76
     verz
    0.75
     ANZ
    0.74
    LZ
    0.73
    RZ
    0.71
     MZ
    0.70
     Heinz
    0.69
    usz
    0.68
     clazz
    0.68
    artz
    0.67
    Act Density 0.002%

    No Known Activations