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

    Neuronpedia

    INDEX
    Explanations

    Informal writing

    np_max-act · gemini-2.0-flash

    This neuron detects first‐person self‐references and personal reflections (I, me, my, what I …).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Parcel
    -0.07
        		↵
    -0.07
    rido
    -0.07
     Ya
    -0.06
     Shield
    -0.06
    (rename
    -0.06
    Metrics
    -0.06
    sand
    -0.06
    Sampler
    -0.06
     Tamil
    -0.06
    POSITIVE LOGITS
     výkon
    0.07
    ullah
    0.06
    getPosition
    0.06
    -ip
    0.06
    .UserName
    0.06
    BOOLE
    0.06
     Dob
    0.06
    pic
    0.06
    РСР
    0.06
     vyrá
    0.06
    Act Density 0.186%

    No Known Activations