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

    Neuronpedia

    INDEX
    Explanations

    Boolean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     présente
    -0.07
    ategy
    -0.06
     HOLDER
    -0.06
     Worker
    -0.06
     Accessibility
    -0.06
    蒐集
    -0.06
    /target
    -0.06
     habe
    -0.06
     Алексан
    -0.06
     Mov
    -0.06
    POSITIVE LOGITS
    اريخ
    0.08
    只要你
    0.07
     );↵↵↵
    0.07
    getExtension
    0.07
    裳
    0.07
    Ố
    0.07
    �
    0.07
     ;;
    0.06
     @_
    0.06
    Directions
    0.06
    Act Density 0.033%

    No Known Activations