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

    Neuronpedia

    INDEX
    Explanations

    AI, purpose, control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ฐ
    0.51
    PROTOCOL
    0.49
    algebra
    0.49
    judgment
    0.48
    identity
    0.48
    บุคคล
    0.47
    Differential
    0.47
    ਰ
    0.46
    indicated
    0.45
     もう
    0.45
    POSITIVE LOGITS
    iamen
    0.51
     execut
    0.44
     actifs
    0.43
     sammen
    0.43
     \,\
    0.43
     masch
    0.42
     "&#
    0.42
    ல்லிய
    0.41
     modell
    0.41
     backlinks
    0.41
    Act Density 0.005%

    No Known Activations