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

    Neuronpedia

    INDEX
    Explanations

    Citation reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    languages
    -0.07
     Language
    -0.07
    スカ
    -0.07
    .FIELD
    -0.06
     Measures
    -0.06
     Facilities
    -0.06
     LENGTH
    -0.06
     больше
    -0.06
    ча
    -0.06
    ーニ
    -0.06
    POSITIVE LOGITS
     foundations
    0.07
     rotor
    0.06
     Paypal
    0.06
     bool
    0.06
     robot
    0.06
     malt
    0.06
    增
    0.06
     wp
    0.06
     headphone
    0.06
    Rights
    0.06
    Act Density 0.002%

    No Known Activations