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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     놀
    -0.07
     �
    -0.06
    	mesh
    -0.06
    웠
    -0.06
    雅黑
    -0.06
     useForm
    -0.06
    managed
    -0.06
    ()).
    -0.06
    bruary
    -0.06
    (||
    -0.06
    POSITIVE LOGITS
    atoes
    0.07
    بي
    0.07
    ators
    0.06
    estination
    0.06
     admin
    0.06
     реє
    0.06
    kaç
    0.06
    erva
    0.06
    strukce
    0.06
    shots
    0.06
    Act Density 0.001%

    No Known Activations