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

    Neuronpedia

    INDEX
    Explanations

    actual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haste
    -0.06
     cm
    -0.06
     최저
    -0.06
     Locator
    -0.06
    	Public
    -0.06
    .coeff
    -0.06
    .DecimalField
    -0.06
     luxurious
    -0.06
    .Series
    -0.06
    .medium
    -0.06
    POSITIVE LOGITS
    =*
    0.07
     tarih
    0.07
     dern
    0.07
     actually
    0.06
     Rewards
    0.06
    LOCATION
    0.06
    constraints
    0.06
    мен
    0.06
    "",↵
    0.06
     robots
    0.06
    Act Density 0.035%

    No Known Activations