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

    Neuronpedia

    INDEX
    Explanations

    2. followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mâc
    0.54
    Sdk
    0.45
    ڑے
    0.43
    کریاں
    0.43
     উঠতে
    0.42
     دلیل
    0.42
    ையைக்
    0.42
    总之
    0.42
    籶
    0.41
    ሱስ
    0.41
    POSITIVE LOGITS
    pro
    0.46
    simple
    0.45
     PRO
    0.42
    gra
    0.41
    glob
    0.40
    А
    0.40
    [\
    0.39
     /
    0.39
    PRO
    0.39
    lum
    0.39
    Act Density 0.000%

    No Known Activations