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

    Neuronpedia

    INDEX
    Explanations

    lucky Poison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rinsic
    0.38
     Kag
    0.37
     হীরু
    0.36
    arono
    0.36
    诠
    0.36
    作
    0.35
    ergy
    0.35
    Hamm
    0.34
     gab
    0.34
    潾
    0.34
    POSITIVE LOGITS
     aceler
    0.40
     Contra
    0.39
     Unle
    0.38
     accél
    0.38
     couldnt
    0.38
     അമ്മ
    0.37
     upset
    0.37
    IVOS
    0.37
     уско
    0.37
     zer
    0.37
    Act Density 0.000%

    No Known Activations