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

    Neuronpedia

    INDEX
    Explanations

    privacy-focused users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     negligence
    0.49
    lined
    0.47
     fiber
    0.47
     dependence
    0.46
     fibr
    0.46
    flin
    0.46
     perine
    0.46
     polymer
    0.45
    ften
    0.45
     dined
    0.45
    POSITIVE LOGITS
     şark
    0.57
    рованный
    0.57
     النرويج
    0.56
    ය
    0.55
    Mont
    0.54
    acji
    0.54
    ს
    0.52
     disputa
    0.51
    说
    0.51
    韩国
    0.50
    Act Density 0.000%

    No Known Activations