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

    Neuronpedia

    INDEX
    Explanations

    causes of death

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    痍
    -0.09
     Monaco
    -0.08
     Species
    -0.08
    طن
    -0.07
    atching
    -0.07
    黩
    -0.07
     Catholics
    -0.07
     }};↵
    -0.07
     childbirth
    -0.07
    سطين
    -0.07
    POSITIVE LOGITS
    퇼
    0.07
    _number
    0.07
     gov
    0.06
    前任
    0.06
    Unavailable
    0.06
    .Hand
    0.06
     stalk
    0.06
    مواجه
    0.06
    ques
    0.06
    晃
    0.06
    Act Density 0.034%

    No Known Activations