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

    Neuronpedia

    INDEX
    Explanations

    contact information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VPN
    0.85
     فی
    0.83
    busy
    0.80
     Untersuchungen
    0.78
     ""
    0.77
     跳
    0.76
     உயர
    0.76
    ulose
    0.75
    ี้ย
    0.75
    gü
    0.75
    POSITIVE LOGITS
    ቃት
    0.61
    uradaki
    0.60
    ਰੇ
    0.60
     nominated
    0.60
    findOrFail
    0.59
     Sald
    0.59
    PAss
    0.58
     complimented
    0.58
    entropic
    0.58
     پرورش
    0.58
    Act Density 0.039%

    No Known Activations