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

    Neuronpedia

    INDEX
    Explanations

    star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Unit
    -0.07
     організації
    -0.07
     teplot
    -0.07
     occupies
    -0.07
     grup
    -0.07
    >Contact
    -0.06
     微
    -0.06
     BuzzFeed
    -0.06
    ysa
    -0.06
    ์และ
    -0.06
    POSITIVE LOGITS
    INS
    0.07
     starred
    0.07
    metric
    0.06
    estro
    0.06
     starring
    0.06
    .sdk
    0.06
    util
    0.06
    居
    0.06
     attraction
    0.06
     Глав
    0.06
    Act Density 0.006%

    No Known Activations