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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nome
    -0.07
    gfx
    -0.07
     molest
    -0.06
     स
    -0.06
    (N
    -0.06
     getX
    -0.06
     çöz
    -0.06
     설치
    -0.06
     yöntem
    -0.06
    ينا
    -0.06
    POSITIVE LOGITS
     registr
    0.07
    atri
    0.06
    94
    0.06
    риг
    0.06
     punitive
    0.06
    spo
    0.06
     valuation
    0.06
     legal
    0.06
     Demo
    0.06
     Legal
    0.06
    Act Density 0.006%

    No Known Activations