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

    Neuronpedia

    INDEX
    Explanations

    soften your gaze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वि
    0.42
     শান্তিপূর্ণ
    0.42
    chyné
    0.40
    네
    0.39
     ne
    0.39
     Ne
    0.39
     نه
    0.39
    荘
    0.39
    眶
    0.39
    莊
    0.38
    POSITIVE LOGITS
     else
    0.47
    fe
    0.44
     gar
    0.40
    Sz
    0.39
     disliked
    0.39
    jala
    0.38
    ella
    0.38
    pre
    0.38
     cutting
    0.38
     prejud
    0.38
    Act Density 0.001%

    No Known Activations