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

    Neuronpedia

    INDEX
    Explanations

    teaching or helping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    돛
    -0.07
     sleeper
    -0.07
     sweets
    -0.07
     McCartney
    -0.07
     целью
    -0.07
     aprender
    -0.07
     rootReducer
    -0.06
    nergie
    -0.06
     Sustainable
    -0.06
     maintain
    -0.06
    POSITIVE LOGITS
    /Public
    0.07
    Persist
    0.07
    -<?
    0.07
    很低
    0.07
    חיפ
    0.07
     =="
    0.06
     hide
    0.06
    讓人
    0.06
     Cars
    0.06
    잍
    0.06
    Act Density 0.143%

    No Known Activations