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

    Neuronpedia

    INDEX
    Explanations

    Torture and violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    暮
    -0.07
     peri
    -0.07
    乃
    -0.07
    Boston
    -0.07
     Clover
    -0.06
     read
    -0.06
    speech
    -0.06
    kwargs
    -0.06
    	client
    -0.06
    xDF
    -0.06
    POSITIVE LOGITS
    .Reflection
    0.07
    .AddInParameter
    0.07
    лен
    0.06
    -European
    0.06
    сий
    0.06
     CrossRef
    0.06
    lovak
    0.06
    alborg
    0.06
    .JPanel
    0.06
    -return
    0.06
    Act Density 0.028%

    No Known Activations