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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting demonstrative pronouns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .lb
    -0.07
     Raymond
    -0.07
     Gould
    -0.07
    .band
    -0.07
    dde
    -0.06
    Band
    -0.06
     cabo
    -0.06
    .addNode
    -0.06
    .opend
    -0.06
     Feder
    -0.06
    POSITIVE LOGITS
    this
    0.10
    "This
    0.08
     this
    0.07
    ţi
    0.07
    	This
    0.07
     that
    0.07
     THIS
    0.07
    (this
    0.07
    that
    0.07
     This
    0.07
    Act Density 0.020%

    No Known Activations