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

    Neuronpedia

    INDEX
    Explanations

    cool Factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     פּ
    0.44
     Cpu
    0.44
    dear
    0.42
     коле
    0.41
     reinst
    0.41
     harass
    0.40
     cpu
    0.40
     CpG
    0.40
     ไหร่
    0.39
     disamb
    0.38
    POSITIVE LOGITS
     😎
    1.02
    😎
    0.81
     dude
    0.67
     dudes
    0.67
     coolness
    0.64
     vibes
    0.64
    dude
    0.64
     factor
    0.63
    io
    0.62
    Factor
    0.61
    Act Density 0.024%

    No Known Activations