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

    Neuronpedia

    INDEX
    Explanations

    viewport

    np_max-act · gemini-2.0-flash

    The neuron detects numeric values in viewport attribute specifications.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sponge
    -0.06
    fak
    -0.06
    /question
    -0.06
     květ
    -0.06
    \Helper
    -0.06
    耀
    -0.06
    _add
    -0.06
     Writer
    -0.06
     миним
    -0.06
    したら
    -0.06
    POSITIVE LOGITS
    oops
    0.08
     bölge
    0.07
    _OscInitStruct
    0.07
    vertices
    0.07
     NSRange
    0.07
     skirm
    0.06
    .getTarget
    0.06
    /inet
    0.06
     dhe
    0.06
    Jeff
    0.06
    Act Density 0.000%

    No Known Activations