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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     쪽지
    -0.07
     sâu
    -0.07
    プ
    -0.07
    _distances
    -0.07
     zaměř
    -0.07
    ník
    -0.07
    ','=
    -0.07
    ології
    -0.06
     школ
    -0.06
    一些
    -0.06
    POSITIVE LOGITS
     Danny
    0.07
    Shopping
    0.06
    	delta
    0.06
     flask
    0.06
     batch
    0.06
    Clone
    0.06
    -year
    0.06
     Dave
    0.06
     hopeless
    0.06
     rave
    0.06
    Act Density 0.000%

    No Known Activations