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

    Neuronpedia

    INDEX
    Explanations

    Script/play lines

    np_max-act · gemini-2.0-flash

    This neuron activates on parenthesized stage directions or character asides (text enclosed in parentheses).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     empirical
    -0.07
     Quality
    -0.07
    わず
    -0.06
     Clips
    -0.06
     됩니다
    -0.06
     Compensation
    -0.06
     yani
    -0.06
    十五
    -0.06
    なんて
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
     dna
    0.08
    oster
    0.06
    бут
    0.06
     °
    0.06
     immigration
    0.06
     exit
    0.06
    arr
    0.06
    麗
    0.06
    Gen
    0.06
    rypto
    0.06
    Act Density 0.015%

    No Known Activations