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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the identifier “smithy” appears (split across tokens) in the generated code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    poses
    -0.07
    Default
    -0.07
     Visualization
    -0.07
    DoubleClick
    -0.06
    preview
    -0.06
    lacağ
    -0.06
    ($("#
    -0.06
    jpg
    -0.06
    _eof
    -0.06
    ुण
    -0.06
    POSITIVE LOGITS
     '"+
    0.07
    τικής
    0.06
    ρωση
    0.06
     SM
    0.06
     داو
    0.06
     getS
    0.06
     Simone
    0.06
    DMETHOD
    0.06
    ți
    0.06
     dept
    0.06
    Act Density 0.000%

    No Known Activations