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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash

    The neuron flags the presence of file‐header license or copyright comment blocks at the top of source files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sung
    -0.07
    icopt
    -0.06
    ização
    -0.06
     gerektir
    -0.06
    くな
    -0.06
     Pink
    -0.06
    ência
    -0.06
    Hex
    -0.06
    -icons
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ]);
    0.07
    -value
    0.07
    Family
    0.06
     �
    0.06
    ();++
    0.06
     cubic
    0.06
     contour
    0.06
    _combined
    0.06
     residency
    0.06
     depended
    0.06
    Act Density 0.000%

    No Known Activations