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

    Neuronpedia

    INDEX
    Explanations

    actions and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uty
    0.37
     CII
    0.36
    utter
    0.36
    Drive
    0.36
    Subscriber
    0.36
    Force
    0.35
    Works
    0.34
     دوا
    0.34
     Portfolio
    0.34
     иностран
    0.34
    POSITIVE LOGITS
     carrot
    0.41
    膏
    0.39
     महंत
    0.38
    otherapist
    0.38
     berry
    0.38
     gom
    0.38
     beeh
    0.38
     smudge
    0.38
    下去
    0.37
     reproduct
    0.37
    Act Density 0.000%

    No Known Activations