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

    Neuronpedia

    INDEX
    Explanations

    textbook

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on mentions of “textbook” (and its plural “textbooks”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     shields
    -0.08
    forcement
    -0.07
    -match
    -0.07
     Gh
    -0.07
     predictions
    -0.07
     Fitz
    -0.06
     Advice
    -0.06
     Juice
    -0.06
     Detect
    -0.06
    .diag
    -0.06
    POSITIVE LOGITS
     textbook
    0.08
    ением
    0.07
    CGFloat
    0.06
    stone
    0.06
     tej
    0.06
     Tobacco
    0.06
    0.06
     Ear
    0.06
    очный
    0.06
     дитини
    0.06
    Act Density 0.003%

    No Known Activations