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

    Neuronpedia

    INDEX
    Explanations

    jaw, infuriating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     belt
    0.43
    CONCLUS
    0.42
    belt
    0.40
    मार
    0.40
    சிக்கும்
    0.39
    lEdit
    0.39
    ства
    0.38
    ర్
    0.38
    epe
    0.38
    ƒ
    0.38
    POSITIVE LOGITS
     contributing
    0.40
    sonic
    0.40
     Jonathan
    0.38
     omitting
    0.38
     Dra
    0.37
     Loài
    0.36
     Romana
    0.36
     ظل
    0.35
     Java
    0.35
    angered
    0.35
    Act Density 0.000%

    No Known Activations