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

    Neuronpedia

    INDEX
    Explanations

    python method definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    0.87
     //</
    0.82
    সন্
    0.78
    öffent
    0.75
    ából
    0.74
    but
    0.74
    ंदोल
    0.73
    等等
    0.73
     Anwar
    0.73
    putchar
    0.72
    POSITIVE LOGITS
    def
    1.96
     def
    1.70
     Def
    1.37
     DEF
    1.19
     definit
    1.14
     defi
    1.14
     deff
    1.05
    Def
    1.02
     definitely
    1.00
    ndef
    0.98
    Act Density 0.079%

    No Known Activations