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

    Neuronpedia

    INDEX
    Explanations

    ownership or organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    裘
    -0.08
    (ml
    -0.07
    isdiction
    -0.07
     Witnesses
    -0.07
     hoof
    -0.07
    ᕛ
    -0.07
    igned
    -0.07
    hs
    -0.07
    uf
    -0.07
    _grad
    -0.07
    POSITIVE LOGITS
    AMB
    0.07
    STEP
    0.07
     reckless
    0.07
    没必要
    0.06
    rijk
    0.06
     holistic
    0.06
    �
    0.06
    ernals
    0.06
    علام
    0.06
     المركز
    0.06
    Act Density 0.093%

    No Known Activations