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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foolish
    -0.07
     �
    -0.06
     شاخ
    -0.06
    ål
    -0.06
     внеш
    -0.06
    ��
    -0.06
    ivable
    -0.06
     clumsy
    -0.06
    ليل
    -0.06
     INCIDENT
    -0.06
    POSITIVE LOGITS
    ��取
    0.06
     gefunden
    0.06
    であった
    0.06
    Excellent
    0.06
    74
    0.06
    233
    0.06
     covering
    0.06
    ESH
    0.06
    @AllArgsConstructor
    0.06
    StartElement
    0.06
    Act Density 0.000%

    No Known Activations