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

    Neuronpedia

    INDEX
    Explanations

    vital signs; fine tune

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.59
     of
    0.55
    olo
    0.52
    ously
    0.52
    la
    0.52
    oint
    0.49
     stri
    0.48
    o
    0.47
    un
    0.47
    owing
    0.46
    POSITIVE LOGITS
    Break
    0.52
     Гуляць
    0.49
    Lyric
    0.49
     IFSC
    0.47
    Weblinks
    0.47
    RelativeLayout
    0.47
    కరణ
    0.46
    Dark
    0.46
    Permissions
    0.46
    ціа
    0.46
    Act Density 0.000%

    No Known Activations