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

    Neuronpedia

    INDEX
    Explanations

    happens through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     helpless
    0.51
    Aslamualaikum
    0.50
     inconvenient
    0.48
     Djokovic
    0.48
     incontinence
    0.48
     prohibitive
    0.47
     مسجد
    0.46
    ꫝ
    0.45
     wicker
    0.45
    巾
    0.45
    POSITIVE LOGITS
    deployRoot
    0.44
    apro
    0.42
    ib
    0.42
    Um
    0.42
     getMenuInflater
    0.40
    esu
    0.39
     serialize
    0.39
    ondata
    0.39
    Vx
    0.39
    0.38
    Act Density 0.026%

    No Known Activations