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

    Neuronpedia

    INDEX
    Explanations

    alongside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pivot
    -0.07
     paperwork
    -0.07
     Robot
    -0.07
     poo
    -0.07
    estation
    -0.07
     errors
    -0.07
     tear
    -0.07
    .aws
    -0.07
    aton
    -0.07
    ィ
    -0.07
    POSITIVE LOGITS
    胪
    0.08
    㮾
    0.08
    诧
    0.08
    咣
    0.08
     שם
    0.07
     אכן
    0.07
     AssemblyCompany
    0.07
     traditionally
    0.07
    这块
    0.07
    跟她
    0.06
    Act Density 0.014%

    No Known Activations