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

    Neuronpedia

    INDEX
    Explanations

    strong descriptive intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pole
    0.42
     እንቅስቃሴ
    0.40
     Somewhat
    0.40
     enlev
    0.39
     checkIf
    0.38
     조금
    0.37
     somewhat
    0.37
     Greatest
    0.37
     উৎ
    0.37
    有时
    0.37
    POSITIVE LOGITS
     wicked
    0.92
     seriously
    0.91
     damn
    0.91
     killer
    0.90
     nasty
    0.84
     serious
    0.81
     legit
    0.81
     badass
    0.81
     brutal
    0.80
     sick
    0.77
    Act Density 0.049%

    No Known Activations