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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is looking for decimal numbers (floating-point numeric literals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Toyota
    -0.07
     reconstruction
    -0.07
    takes
    -0.06
    rad
    -0.06
     heute
    -0.06
     Asp
    -0.06
     �
    -0.06
    Race
    -0.06
     Maiden
    -0.06
     McCartney
    -0.06
    POSITIVE LOGITS
     určit
    0.07
    920
    0.06
     initWithFrame
    0.06
    ////////////////////////////////
    0.06
    []
↵
    0.06
     Smile
    0.06
    .Bool
    0.06
    945
    0.06
    .BO
    0.06
    責
    0.06
    Act Density 0.029%

    No Known Activations