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

    Neuronpedia

    INDEX
    Explanations

    respectively

    np_max-act · gemini-2.0-flash

    This neuron fires on floating‐point numeric tokens (decimal numbers with multiple digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     над
    -0.07
     fraught
    -0.07
     kaum
    -0.07
     Đề
    -0.06
    ainless
    -0.06
    ileen
    -0.06
     nhuận
    -0.06
    MY
    -0.06
    .onSubmit
    -0.06
     gamm
    -0.06
    POSITIVE LOGITS
     whopping
    0.07
     markdown
    0.07
     respectively
    0.06
     Soon
    0.06
     sadly
    0.06
    ipeg
    0.06
     OTP
    0.06
     Tol
    0.06
     機
    0.06
     philosophers
    0.06
    Act Density 0.009%

    No Known Activations