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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    finalize
    -0.07
     tele
    -0.07
    calar
    -0.07
     Secondary
    -0.06
     socioeconomic
    -0.06
     Similar
    -0.06
    ollower
    -0.06
    Adds
    -0.06
    高い
    -0.06
     gradually
    -0.06
    POSITIVE LOGITS
     goggles
    0.07
     aseg
    0.06
    design
    0.06
     авг
    0.06
    nič
    0.06
     خش
    0.06
     utilizing
    0.06
    /effects
    0.06
    ottle
    0.06
    !]
    0.06
    Act Density 0.005%

    No Known Activations