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

    Neuronpedia

    INDEX
    Explanations

    sybil attack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sanity
    0.49
    anno
    0.40
     goofy
    0.40
    วิ่ง
    0.40
    dayspecial
    0.39
     خطوات
    0.39
    ùm
    0.38
    liv
    0.38
    ousse
    0.38
     manages
    0.38
    POSITIVE LOGITS
    цией
    0.41
     Incl
    0.39
     Names
    0.38
     Cim
    0.38
     cr
    0.38
     Huntingdon
    0.38
    Incl
    0.37
    猚
    0.37
     Vegetables
    0.37
    lores
    0.36
    Act Density 0.000%

    No Known Activations