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

    Neuronpedia

    INDEX
    Explanations

    sensitive information, status

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sever
    0.92
    Inter
    0.87
    Dep
    0.87
    الب
    0.84
    Cách
    0.82
    Pupp
    0.82
    Sebelum
    0.80
    Chu
    0.80
    Sud
    0.78
    LAG
    0.78
    POSITIVE LOGITS
    í
    1.16
    ek
    0.99
    jects
    0.93
    ş
    0.91
    ż
    0.85
    ž
    0.83
     g
    0.82
    ží
    0.81
    𝕜
    0.76
     shrinks
    0.75
    Act Density 0.000%

    No Known Activations