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

    Neuronpedia

    INDEX
    Explanations

    histories of, Text panel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۳
    0.49
     ۴
    0.46
     እንኳን
    0.46
    rakk
    0.44
     universally
    0.43
     ディ
    0.43
     head
    0.43
     soaked
    0.42
     හ
    0.42
     forbidden
    0.42
    POSITIVE LOGITS
    叅
    0.47
    า
    0.46
     operat
    0.45
    Presets
    0.45
    ยายน
    0.45
    亣
    0.45
     wyn
    0.44
    परे
    0.44
    ertown
    0.44
    㑹
    0.44
    Act Density 0.001%

    No Known Activations