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

    Neuronpedia

    INDEX
    Explanations

    Methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contracts
    -0.07
     schwer
    -0.07
     ADC
    -0.07
    ogle
    -0.07
     lg
    -0.07
    stop
    -0.06
     progn
    -0.06
    ườ
    -0.06
     chk
    -0.06
    561
    -0.06
    POSITIVE LOGITS
    :data
    0.07
    .newArrayList
    0.06
    .cart
    0.06
    management
    0.06
    _Current
    0.06
    =False
    0.06
    (month
    0.06
     /*↵
    0.06
    	java
    0.06
    .MiddleCenter
    0.05
    Act Density 0.003%

    No Known Activations