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

    Neuronpedia

    INDEX
    Explanations

    Software licenses/packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    安东
    -0.07
    =<?=$
    -0.07
    _RF
    -0.07
    を集
    -0.07
    毛
    -0.07
    魂
    -0.07
    臼
    -0.07
    (_("
    -0.07
    隆重
    -0.07
    (\$
    -0.07
    POSITIVE LOGITS
     hayatını
    0.09
     UART
    0.07
     댓
    0.07
     diff
    0.06
    prog
    0.06
     eviction
    0.06
    �
    0.06
     Lawyer
    0.06
    �
    0.06
     thuisontvangst
    0.06
    Act Density 0.001%

    No Known Activations