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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     henüz
    -0.07
     reluctantly
    -0.07
    忙
    -0.06
     kad
    -0.06
     attempting
    -0.06
    uggling
    -0.06
     dado
    -0.06
     carved
    -0.06
     metav
    -0.06
     CONVERT
    -0.06
    POSITIVE LOGITS
     is
    0.17
     Is
    0.12
     IS
    0.12
    —is
    0.12
    ,is
    0.11
     isn
    0.11
    	is
    0.11
     are
    0.09
    is
    0.09
    Is
    0.09
    Act Density 1.721%

    No Known Activations