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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    OC
    -0.07
     досвід
    -0.07
    ництва
    -0.07
     enerji
    -0.06
    ethyl
    -0.06
    ченко
    -0.06
    �n
    -0.06
    kovou
    -0.06
     nebude
    -0.06
    POSITIVE LOGITS
     numer
    0.08
    .setDescription
    0.07
     stamped
    0.07
     formula
    0.06
    numer
    0.06
     Completion
    0.06
     planning
    0.06
     arrangement
    0.06
    .serializer
    0.06
    .cb
    0.06
    Act Density 0.003%

    No Known Activations