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

    Neuronpedia

    INDEX
    Explanations

    either

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нення
    -0.07
     σχέ
    -0.07
    Runs
    -0.07
     推
    -0.07
     Floyd
    -0.06
     administering
    -0.06
     Surg
    -0.06
    949
    -0.06
    เภ
    -0.06
    969
    -0.06
    POSITIVE LOGITS
     either
    0.16
    either
    0.09
    :j
    0.06
     petit
    0.06
    	expected
    0.06
    -second
    0.06
     directory
    0.06
    :selected
    0.06
     ثلاث
    0.06
     abbrev
    0.06
    Act Density 0.011%

    No Known Activations