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

    Neuronpedia

    INDEX
    Explanations

    rule 34 porn or unusual emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िरिक्स
    0.56
    mainan
    0.51
     എന്നാൽ
    0.50
     fût
    0.48
     fas
    0.47
     sustancias
    0.47
    )}=
    0.46
     Шрифт
    0.46
     Nachricht
    0.46
     marvellous
    0.46
    POSITIVE LOGITS
    3
    0.46
    wy
    0.46
    de
    0.45
    Fluor
    0.44
    J
    0.43
    Mem
    0.42
    dump
    0.42
     Canyon
    0.41
    larında
    0.41
     dumping
    0.41
    Act Density 0.006%

    No Known Activations