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

    Neuronpedia

    INDEX
    Explanations

    ml

    np_max-act · gemini-2.0-flash

    The neuron is specialized to pick out the “ldml” XML tags (and related LDML/DOCTYPE markers) in Unicode locale‐data documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Viol
    -0.07
    ANDROID
    -0.07
     defensive
    -0.07
    _toggle
    -0.06
     rex
    -0.06
    temp
    -0.06
    .check
    -0.06
    _Num
    -0.06
    Filtered
    -0.06
     video
    -0.06
    POSITIVE LOGITS
     fantasy
    0.06
     PHP
    0.06
    воля
    0.06
     feasible
    0.06
     muscles
    0.06
     �
    0.06
     steer
    0.06
     login
    0.06
     compliance
    0.06
     tone
    0.06
    Act Density 0.001%

    No Known Activations