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

    Neuronpedia

    INDEX
    Explanations

    say "/"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ियर
    -0.07
     charitable
    -0.07
    ERICAN
    -0.07
     according
    -0.06
     output
    -0.06
     Cout
    -0.06
    βέρ
    -0.06
    beg
    -0.06
     تسم
    -0.06
     today
    -0.06
    POSITIVE LOGITS
    .Bus
    0.06
     autoimmune
    0.06
     الوص
    0.06
    Validators
    0.06
    rpc
    0.06
     ladies
    0.06
     JAXBElement
    0.06
    .Cookies
    0.06
    SuppressLint
    0.06
    эй
    0.06
    Act Density 0.011%

    No Known Activations