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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on isolated capital‐letter initials followed by a period, i.e. author or editor initials in citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     white
    -0.07
    _r
    -0.07
    ,rp
    -0.07
    ，如
    -0.06
     Categories
    -0.06
    _Draw
    -0.06
     trails
    -0.06
     Souls
    -0.06
     marsh
    -0.06
    Code
    -0.06
    POSITIVE LOGITS
    .mozilla
    0.07
     ByteBuffer
    0.06
    shader
    0.06
    рож
    0.06
     Nous
    0.06
    λλι
    0.06
    ี.
    0.06
    skou
    0.06
    .SERVER
    0.06
     Pablo
    0.06
    Act Density 0.014%

    No Known Activations