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

    Neuronpedia

    INDEX
    Explanations

    Ark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nos
    -0.07
    主要是
    -0.07
     rencontre
    -0.07
    זמנים
    -0.07
     gastrointestinal
    -0.07
     troop
    -0.07
    𫇭
    -0.06
     talks
    -0.06
     strikes
    -0.06
     reproductive
    -0.06
    POSITIVE LOGITS
    fi
    0.07
    umph
    0.07
    ucson
    0.07
     Recorder
    0.07
    bound
    0.07
    icensing
    0.07
    Late
    0.06
    _TOPIC
    0.06
     שוב
    0.06
    وظ
    0.06
    Act Density 0.001%

    No Known Activations