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

    Neuronpedia

    INDEX
    Explanations

    -in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SupportedException
    -0.07
     discoveries
    -0.07
     JpaRepository
    -0.07
    foods
    -0.07
    /address
    -0.06
     perfectly
    -0.06
    William
    -0.06
    报仇
    -0.06
    _transfer
    -0.06
    pickup
    -0.06
    POSITIVE LOGITS
    -bot
    0.06
     earthly
    0.06
    pis
    0.06
     *\
    0.06
    Ey
    0.06
    (fake
    0.06
    atég
    0.06
    ass
    0.06
     HERO
    0.06
    🅢
    0.06
    Act Density 0.000%

    No Known Activations