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

    Neuronpedia

    INDEX
    Explanations

    expressing confidence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🅐
    -0.07
    -->
    -0.07
    еньк
    -0.07
    传真
    -0.07
    📎
    -0.07
     spree
    -0.06
    🅚
    -0.06
    -packages
    -0.06
     takeover
    -0.06
    oundary
    -0.06
    POSITIVE LOGITS
     motorcycles
    0.07
    omite
    0.07
     solids
    0.07
     randomized
    0.07
     alloy
    0.07
     commodo
    0.07
     permitted
    0.07
    ders
    0.07
    kg
    0.07
    ISING
    0.06
    Act Density 0.045%

    No Known Activations