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

    Neuronpedia

    INDEX
    Explanations

    loud and clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pull
    0.62
     Paglin
    0.61
     Penet
    0.60
     revisão
    0.59
    重要的是
    0.59
     Set
    0.58
     Out
    0.57
     kull
    0.57
     hitt
    0.56
     طی
    0.56
    POSITIVE LOGITS
     رکھے
    0.79
    alunos
    0.75
     propias
    0.73
    ographically
    0.73
     স্নাতক
    0.72
    grupo
    0.72
    Grupo
    0.71
    锄
    0.70
    卆
    0.69
    ancies
    0.69
    Act Density 0.000%

    No Known Activations