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

    Neuronpedia

    INDEX
    Explanations

    listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larla
    0.62
    használ
    0.62
    ların
    0.61
    ierto
    0.61
    ább
    0.61
     respostas
    0.60
     நாட்க
    0.60
    assapi
    0.60
    ୩
    0.59
    larının
    0.59
    POSITIVE LOGITS
    Since
    0.57
     Churches
    0.57
     Since
    0.56
     code
    0.55
     Companies
    0.54
     If
    0.53
    然后
    0.52
    Companies
    0.52
    再一次
    0.52
     Convention
    0.52
    Act Density 0.071%

    No Known Activations