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

    Neuronpedia

    INDEX
    Explanations

    os

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     andra
    -0.07
    _basename
    -0.07
     Victims
    -0.06
    ده
    -0.06
     hóa
    -0.06
     FAIL
    -0.06
    _after
    -0.06
    дорож
    -0.06
     females
    -0.06
     surv
    -0.06
    POSITIVE LOGITS
    .LogError
    0.07
    entityManager
    0.07
    ephir
    0.07
    ')}}
    0.06
    鞳
    0.06
    聿
    0.06
     embodied
    0.06
    玦
    0.06
     PyQt
    0.06
    .Server
    0.06
    Act Density 0.001%

    No Known Activations