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

    Neuronpedia

    INDEX
    Explanations

    ratios

    np_max-act · gemini-2.0-flash

    The neuron never activates on any tokens—it’s essentially a “dead” neuron that doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    repair
    -0.07
     Barbara
    -0.06
     performed
    -0.06
     Counter
    -0.06
    liers
    -0.06
     counter
    -0.06
     college
    -0.06
     lowest
    -0.06
     iterating
    -0.06
     spinal
    -0.06
    POSITIVE LOGITS
     duygu
    0.07
     FileType
    0.07
     собой
    0.07
    (Target
    0.06
    ้เป
    0.06
    ℃
    0.06
    猪
    0.06
    posables
    0.06
    ـــ
    0.06
    .ceil
    0.06
    Act Density 0.011%

    No Known Activations