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

    Neuronpedia

    INDEX
    Explanations

    error checking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poison
    -0.08
     Pieces
    -0.07
    MainThread
    -0.07
     chest
    -0.07
    ต
    -0.07
    Levels
    -0.07
    _input
    -0.07
    Cls
    -0.07
    _sql
    -0.07
    型
    -0.07
    POSITIVE LOGITS
     zách
    0.06
     그녀
    0.06
    ้าส
    0.06
    (guild
    0.06
    overy
    0.06
    �
    0.06
     pursuits
    0.06
     ASTM
    0.06
     endIndex
    0.05
     �
    0.05
    Act Density 0.110%

    No Known Activations