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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timber
    -0.07
    onyms
    -0.07
    -за
    -0.06
    RIORITY
    -0.06
     front
    -0.06
     wool
    -0.06
     등장
    -0.06
    -entity
    -0.06
     tutoring
    -0.06
    targets
    -0.06
    POSITIVE LOGITS
     deficit
    0.06
    ợi
    0.06
    edl
    0.06
     الطب
    0.06
     abdom
    0.06
    uem
    0.06
    ifornia
    0.06
    ура
    0.06
    uy�
    0.06
     encount
    0.06
    Act Density 0.069%

    No Known Activations