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

    Neuronpedia

    INDEX
    Explanations

    crisis text line instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    balls
    0.67
    subjects
    0.65
     sun
    0.65
    الك
    0.65
    Wish
    0.64
     subjects
    0.64
    glb
    0.62
    ঠে
    0.62
    Pe
    0.62
    ંધ
    0.61
    POSITIVE LOGITS
     PopupWindow
    0.63
    ույ
    0.63
    aligned
    0.61
    configFile
    0.61
     حساب
    0.58
     쪽
    0.58
    洒落
    0.58
    覆盖
    0.57
    arto
    0.57
     impr
    0.57
    Act Density 0.175%

    No Known Activations