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

    Neuronpedia

    INDEX
    Explanations

    Organizations and Publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lain
    -0.07
    宰
    -0.07
     sis
    -0.07
     razón
    -0.06
    bies
    -0.06
    _PATTERN
    -0.06
    食品
    -0.06
    .getPlayer
    -0.06
    OLON
    -0.06
     jim
    -0.06
    POSITIVE LOGITS
     classification
    0.07
     pagina
    0.07
    acht
    0.07
    出道
    0.06
    规范化
    0.06
     session
    0.06
    经验丰富
    0.06
    犯罪
    0.06
    Payload
    0.06
    无可
    0.06
    Act Density 0.191%

    No Known Activations