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

    Neuronpedia

    INDEX
    Explanations

    emotional and physical sensations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ре
    1.75
    我认为
    1.69
    లో
    1.67
     смотри
    1.63
    观看
    1.61
    如下图
    1.59
     зри
    1.57
    composed
    1.57
     اوقات
    1.57
     ساخت
    1.54
    POSITIVE LOGITS
     grooves
    1.59
     vibrations
    1.41
    EntryPoint
    1.40
    ties
    1.36
    他の
    1.35
    们
    1.33
    tol
    1.29
     vibration
    1.28
    ...+
    1.28
     firsthand
    1.26
    Act Density 0.135%

    No Known Activations