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

    Neuronpedia

    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instit
    -0.06
    Mil
    -0.06
     uncompressed
    -0.06
    Islam
    -0.06
    _social
    -0.06
    Sparse
    -0.06
    ��
    -0.06
    Jvm
    -0.06
    	scanf
    -0.06
     developmental
    -0.06
    POSITIVE LOGITS
    .Physics
    0.07
    ินการ
    0.07
    曰
    0.06
    onsense
    0.06
    τισ
    0.06
     FITNESS
    0.06
    -------↵
    0.06
    ;↵↵↵↵↵
    0.06
     ней
    0.06
     Throws
    0.06
    Act Density 0.004%

    No Known Activations