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

    Neuronpedia

    INDEX
    Explanations

    malware, medical conditions, context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    1.14
    June
    1.13
    tilde
    1.06
     cư
    1.06
    同步
    1.06
    hood
    1.02
    하며
    1.00
     निरीक्षण
    0.99
    organization
    0.98
    ever
    0.96
    POSITIVE LOGITS
     kisah
    1.35
    нка
    1.20
    Keefe
    1.18
     коль
    1.16
    aca
    1.16
    ğa
    1.15
    ierten
    1.13
     maxx
    1.11
     letto
    1.10
     benzyl
    1.10
    Act Density 0.001%

    No Known Activations