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

    Neuronpedia

    INDEX
    Explanations

    error messages, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rental
    -0.07
     s
    -0.06
    .session
    -0.06
    .elem
    -0.06
    COM
    -0.06
    іт
    -0.06
     optimistic
    -0.06
    ambda
    -0.06
    -orders
    -0.06
    cu
    -0.06
    POSITIVE LOGITS
     har
    0.08
    基于
    0.07
    0.07
    0.07
    0.07
     poté
    0.06
    (TokenType
    0.06
     Stability
    0.06
     bitterly
    0.06
    0.06
    Act Density 0.008%

    No Known Activations