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

    Neuronpedia

    INDEX
    Explanations

    explaining or defining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destitute
    0.94
     violent
    0.87
    于是
    0.84
    その
    0.82
     consolation
    0.81
    ї
    0.81
     communal
    0.80
     Christmas
    0.79
     longtime
    0.79
     solemn
    0.78
    POSITIVE LOGITS
    lm
    1.26
    ln
    1.11
    ne
    1.09
    lv
    1.06
    li
    1.03
    م
    1.02
    lab
    1.02
    la
    1.01
    lere
    1.00
    ljen
    1.00
    Act Density 0.000%

    No Known Activations