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

    Neuronpedia

    INDEX
    Explanations

    software installation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     USSR
    -0.08
    frm
    -0.08
    \Image
    -0.07
    公布
    -0.07
    .fromCharCode
    -0.07
     furnish
    -0.07
    approval
    -0.07
     weird
    -0.07
    قوم
    -0.07
    温馨
    -0.07
    POSITIVE LOGITS
    쥡
    0.07
    颡
    0.07
     Lesson
    0.07
    研究员
    0.07
    鄣
    0.06
    Hora
    0.06
    胍
    0.06
    (CancellationToken
    0.06
     bask
    0.06
    istical
    0.06
    Act Density 0.064%

    No Known Activations