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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Applicant
    -0.07
    Watcher
    -0.06
     خم
    -0.06
    el
    -0.06
    는지
    -0.06
    棒
    -0.06
     Steele
    -0.06
     unspecified
    -0.06
    .configuration
    -0.06
    ilih
    -0.06
    POSITIVE LOGITS
     كتب
    0.07
    acji
    0.07
     creat
    0.07
    ricula
    0.06
    .adapters
    0.06
     Tokens
    0.06
     libros
    0.06
     Giáo
    0.06
     increased
    0.06
    GridLayout
    0.06
    Act Density 0.211%

    No Known Activations