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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unicode
    -0.07
    EEE
    -0.06
    aming
    -0.06
     Up
    -0.06
    EFI
    -0.06
    ampire
    -0.06
    Você
    -0.06
    women
    -0.06
     coolant
    -0.06
     converts
    -0.06
    POSITIVE LOGITS
     вироб
    0.07
    _Dep
    0.07
     strawberries
    0.07
    谱
    0.07
    _point
    0.06
    �情
    0.06
     stepper
    0.06
     تاریخی
    0.06
     губер
    0.06
    reglo
    0.06
    Act Density 0.011%

    No Known Activations