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

    Neuronpedia

    INDEX
    Explanations

    subject (in code)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _New
    -0.07
    Arr
    -0.07
     мог
    -0.07
    逃
    -0.06
    γραφή
    -0.06
     loro
    -0.06
     Algeria
    -0.06
     edt
    -0.06
     FOX
    -0.06
     Names
    -0.06
    POSITIVE LOGITS
    SetTitle
    0.07
    	sound
    0.06
    -faced
    0.06
     Padding
    0.06
    _CC
    0.06
    	rb
    0.06
    )↵↵↵↵↵↵↵↵
    0.06
     buyers
    0.06
    ORM
    0.06
     probable
    0.06
    Act Density 0.006%

    No Known Activations