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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     localStorage
    -0.07
     �
    -0.07
    Arr
    -0.07
    izer
    -0.07
    .copy
    -0.07
    Shar
    -0.07
    юдж
    -0.07
    capitalize
    -0.06
     ubuntu
    -0.06
    025
    -0.06
    POSITIVE LOGITS
    _SUS
    0.07
     stains
    0.06
     Crus
    0.06
    mess
    0.06
     natuur
    0.06
    .labels
    0.06
    運
    0.05
    럭
    0.05
     stained
    0.05
    /mp
    0.05
    Act Density 0.006%

    No Known Activations