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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MESSAGE
    -0.07
    typed
    -0.06
     teasing
    -0.06
    association
    -0.06
     MAK
    -0.06
    .ad
    -0.06
    Offer
    -0.06
     earned
    -0.06
    ализ
    -0.06
    fre
    -0.06
    POSITIVE LOGITS
    川
    0.08
     cr
    0.07
     Miguel
    0.06
     pupper
    0.06
    	action
    0.06
    .extension
    0.06
    <Long
    0.06
    破
    0.06
    張
    0.06
    々
    0.06
    Act Density 0.003%

    No Known Activations