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

    Neuronpedia

    INDEX
    Explanations

    native

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proof
    -0.07
    函
    -0.07
     drills
    -0.06
     hoàn
    -0.06
     Expenses
    -0.06
     инструмент
    -0.06
     withdrawal
    -0.06
    Containers
    -0.06
     capabilities
    -0.06
    Sky
    -0.06
    POSITIVE LOGITS
    .loading
    0.07
    vide
    0.07
    Calibri
    0.07
    centage
    0.06
    %"
    0.06
    ضم
    0.06
     Wrestling
    0.06
     benefici
    0.06
     fullName
    0.06
    ानन
    0.06
    Act Density 0.259%

    No Known Activations