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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schl
    -0.07
     analsex
    -0.07
    쌔
    -0.07
     sürek
    -0.07
    ҝ
    -0.07
     (;;)
    -0.07
    olds
    -0.07
    ſt
    -0.07
    kont
    -0.06
    scss
    -0.06
    POSITIVE LOGITS
    Maximum
    0.07
    資源
    0.07
     communities
    0.07
    kbd
    0.07
    	tr
    0.07
     redirected
    0.07
    Callable
    0.07
    calls
    0.06
    �
    0.06
    收入
    0.06
    Act Density 0.000%

    No Known Activations