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

    Neuronpedia

    INDEX
    Explanations

    Question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .embed
    -0.08
    .Comp
    -0.07
    룀
    -0.07
     educação
    -0.07
    Thickness
    -0.07
    等活动
    -0.07
    芬兰
    -0.07
    -Mar
    -0.07
    打得
    -0.07
     внимание
    -0.07
    POSITIVE LOGITS
    :[
    0.07
    **
↵
    0.07
    催
    0.07
    finally
    0.07
    alah
    0.07
    蟛
    0.06
     ye
    0.06
    eor
    0.06
     עצמ
    0.06
    ynes
    0.06
    Act Density 0.158%

    No Known Activations