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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -console
    -0.07
    Mission
    -0.07
    _ped
    -0.06
    вий
    -0.06
    tí
    -0.06
     Deg
    -0.06
    ardown
    -0.06
     IKE
    -0.06
     Kov
    -0.06
    .dumps
    -0.06
    POSITIVE LOGITS
     sharper
    0.07
     تون
    0.07
     ")"
    0.06
    “He
    0.06
     Himself
    0.06
     mastering
    0.06
     홍
    0.06
     skill
    0.06
    }`
    0.06
     Wells
    0.06
    Act Density 0.039%

    No Known Activations