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

    Neuronpedia

    INDEX
    Explanations

    Raspberry Pi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.75
    <unused1030>
    0.60
    𒌷
    0.59
    <unused1038>
    0.57
     사용자
    0.57
    <unused612>
    0.57
    <unused2063>
    0.57
    <unused371>
    0.56
     задума
    0.56
     Hadid
    0.55
    POSITIVE LOGITS
    ים
    0.70
    et
    0.64
    es
    0.61
    ך
    0.60
     Else
    0.59
    in
    0.58
    כל
    0.58
    at
    0.57
    ↵↵
    0.57
    that
    0.56
    Act Density 0.007%

    No Known Activations