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

    Neuronpedia

    INDEX
    Explanations

    variable assignments

    np_max-act · gemini-2.0-flash

    calculations or mathematical expressions involving comparisons of numerical values.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ped
    -0.07
    lying
    -0.07
     ped
    -0.07
     Gill
    -0.07
     Pays
    -0.06
     shows
    -0.06
    (unique
    -0.06
     algorithm
    -0.06
     presenting
    -0.06
    UPDATE
    -0.06
    POSITIVE LOGITS
     �
    0.07
     nhanh
    0.07
     temin
    0.07
     güven
    0.06
    败
    0.06
    (resourceName
    0.06
     sahibi
    0.06
    .Nav
    0.06
    好了
    0.06
     funciones
    0.06
    Act Density 0.015%

    No Known Activations