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

    Neuronpedia

    INDEX
    Explanations

    investigation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     टेल
    0.59
    scoped
    0.58
    ैम
    0.55
     दिखे
    0.55
     silently
    0.54
    [`
    0.53
    ¹)
    0.53
     }$
    0.52
    ጽ
    0.52
     jugar
    0.52
    POSITIVE LOGITS
     muu
    0.64
     Fir
    0.62
     Delhi
    0.59
     Malay
    0.59
    ACI
    0.59
     Propriet
    0.58
    MANAGER
    0.58
     менедже
    0.58
     Pantai
    0.58
     AMO
    0.57
    Act Density 0.002%

    No Known Activations