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

    Neuronpedia

    INDEX
    Explanations

    Self-references

    np_max-act-logits · gemini-2.0-flash

    The neuron detects first-person self-reference (speaker-focused pronouns and constructions indicating "I"/the narrator).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    illustr
    -0.07
    ポート
    -0.07
     addslashes
    -0.07
    GRADE
    -0.07
    .kind
    -0.06
    ducation
    -0.06
     Values
    -0.06
    ArgumentNullException
    -0.06
     caster
    -0.06
    .Cascade
    -0.06
    POSITIVE LOGITS
     रन
    0.07
    /event
    0.06
    「你
    0.06
    ’yi
    0.06
    ubo
    0.06
     zákona
    0.06
    50
    0.06
    =session
    0.06
     добав
    0.06
    nerRadius
    0.06
    Act Density 0.050%

    No Known Activations