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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dismay
    -0.08
     hebben
    -0.07
    han
    -0.07
     came
    -0.07
     caramel
    -0.07
    mesine
    -0.07
     were
    -0.07
     Egg
    -0.07
     PNG
    -0.06
    Find
    -0.06
    POSITIVE LOGITS
     همراه
    0.07
    .Direction
    0.06
    lico
    0.06
     дал
    0.06
    /datatables
    0.06
     편
    0.06
    .dsl
    0.06
     біля
    0.05
    ////////////////////////////////////////////////////////////////////////////////↵
    0.05
     nuestros
    0.05
    Act Density 0.033%

    No Known Activations