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

    Neuronpedia

    INDEX
    Explanations

    stuffy Noses, Let's, proper security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蟆
    0.48
    ographique
    0.47
    ział
    0.47
     одной
    0.46
     സ്ഥി
    0.46
     আইনে
    0.46
    훔
    0.46
     значення
    0.46
     시간
    0.46
    MNumber
    0.46
    POSITIVE LOGITS
    ↵
    0.52
    ss
    0.40
    chosen
    0.40
    .
    0.40
    osh
    0.39
     Ox
    0.39
     cau
    0.38
    se
    0.38
    et
    0.38
     Load
    0.38
    Act Density 0.000%

    No Known Activations