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

    Neuronpedia

    INDEX
    Explanations

    captives taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stam
    0.43
     US
    0.42
     Piccolo
    0.39
     Imm
    0.38
     Elmer
    0.36
    crypt
    0.36
     Lam
    0.35
     Crypt
    0.35
    US
    0.35
     smuggling
    0.35
    POSITIVE LOGITS
     பதில
    0.44
    ீர்
    0.43
    órias
    0.43
     คะ
    0.43
     شوید
    0.42
    ൂര
    0.40
     रिलेटेड
    0.40
     ór
    0.40
    omètre
    0.40
     conjectures
    0.40
    Act Density 0.002%

    No Known Activations