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

    Neuronpedia

    INDEX
    Explanations

    it sounds like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     રીતે
    0.58
    า
    0.57
    ″
    0.56
    行う
    0.52
    고사
    0.48
    𝑖
    0.47
    िज्या
    0.47
     infile
    0.47
    aporation
    0.46
    ング
    0.46
    POSITIVE LOGITS
    نوع
    0.54
    ItemStack
    0.47
    Mk
    0.46
    các
    0.46
     previsto
    0.46
     liable
    0.46
    ма
    0.45
    ɓ
    0.45
     noticeably
    0.45
     شنو
    0.45
    Act Density 0.024%

    No Known Activations