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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assert
    -0.07
     Solo
    -0.07
     IDENT
    -0.07
     rit
    -0.07
     sync
    -0.07
     gio
    -0.07
     přik
    -0.06
    €�
    -0.06
     mirac
    -0.06
     inform
    -0.06
    POSITIVE LOGITS
     newsletter
    0.07
    (rules
    0.06
    834
    0.06
    _QUOTES
    0.06
    тора
    0.06
    ่าจะ
    0.06
    �
    0.06
    ゛
    0.06
     Saskatchewan
    0.06
    .paging
    0.06
    Act Density 0.035%

    No Known Activations