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

    Neuronpedia

    INDEX
    Explanations

    artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mech
    -0.07
    _car
    -0.07
    شناس
    -0.07
     изуч
    -0.06
    (withDuration
    -0.06
     النو
    -0.06
    ��
    -0.06
     kromě
    -0.06
    .tf
    -0.06
    //--
    -0.06
    POSITIVE LOGITS
     artifacts
    0.07
    ORMAL
    0.07
     artifact
    0.07
     handic
    0.07
    ILI
    0.06
     billed
    0.06
    ilion
    0.06
     manually
    0.06
    arity
    0.06
     still
    0.06
    Act Density 0.002%

    No Known Activations