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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cities
    -0.07
    tokens
    -0.07
     neon
    -0.06
     engagements
    -0.06
     contin
    -0.06
     coolant
    -0.06
     telesc
    -0.06
     οποία
    -0.06
    wil
    -0.06
    sector
    -0.06
    POSITIVE LOGITS
     DIRECT
    0.07
    $MESS
    0.06
     frameborder
    0.06
     thêm
    0.06
    keit
    0.06
     
    0.06
     diversas
    0.06
    sstream
    0.06
     fieldName
    0.06
    一覧
    0.06
    Act Density 0.214%

    No Known Activations