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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preds
    -0.07
    需
    -0.07
     reside
    -0.06
    /../
    -0.06
    named
    -0.06
    osomes
    -0.06
     sole
    -0.06
    	dis
    -0.06
     clearing
    -0.06
    osome
    -0.06
    POSITIVE LOGITS
     {*}
    0.07
     UITextView
    0.06
    Lin
    0.06
     fals
    0.06
    Trivia
    0.06
    (getClass
    0.06
    教授
    0.06
    .ENTER
    0.06
    pong
    0.06
     Böyle
    0.06
    Act Density 0.029%

    No Known Activations