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

    Neuronpedia

    INDEX
    Explanations

    Controversy/strong reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ddl
    -0.06
    บอก
    -0.06
     isLoggedIn
    -0.06
     पह
    -0.06
    (JFrame
    -0.06
     сигн
    -0.06
     Site
    -0.06
    ovy
    -0.06
     천
    -0.06
     Cove
    -0.06
    POSITIVE LOGITS
     '\''
    0.07
     EntityType
    0.06
     التص
    0.06
    .ToolTip
    0.06
     tension
    0.06
    ework
    0.06
    zens
    0.06
    Payment
    0.06
    図
    0.06
    _deep
    0.06
    Act Density 0.130%

    No Known Activations