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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なくて
    -0.08
    basic
    -0.07
     manage
    -0.07
     huge
    -0.07
     prize
    -0.06
    quiring
    -0.06
    	panic
    -0.06
    DIG
    -0.06
     numbers
    -0.06
     dung
    -0.06
    POSITIVE LOGITS
    ḵ
    0.08
    rah
    0.07
     לעומת
    0.07
    擦拭
    0.07
    �
    0.07
    ])));↵
    0.07
    .instances
    0.07
    centroid
    0.06
     appréci
    0.06
    ѵ
    0.06
    Act Density 0.001%

    No Known Activations