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

    Neuronpedia

    INDEX
    Explanations

    crashing down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Direct
    0.43
     العامل
    0.40
    )+\
    0.38
     कुलकर्णी
    0.38
    频谱
    0.37
     thread
    0.36
     कर्मचारी
    0.36
     hectares
    0.36
     Contains
    0.36
     threads
    0.36
    POSITIVE LOGITS
    吘
    0.43
    izlik
    0.41
    のデザイン
    0.38
    cial
    0.38
    İ
    0.37
     ocult
    0.37
    çı
    0.36
    rq
    0.36
    re
    0.36
    დება
    0.36
    Act Density 0.001%

    No Known Activations