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

    Neuronpedia

    INDEX
    Explanations

    Nonsense text/errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lete
    -0.08
     musu
    -0.07
    Conexion
    -0.07
     mercado
    -0.07
     rumah
    -0.07
     मोब
    -0.07
     ester
    -0.07
    luv
    -0.07
     remedies
    -0.07
    ustele
    -0.07
    POSITIVE LOGITS
    乱码
    0.11
    亂
    0.10
    Oops
    0.09
     étrange
    0.09
     untranslated
    0.09
     spontan
    0.09
     inadvertently
    0.09
    cluded
    0.09
     prematurely
    0.08
    乱
    0.08
    Act Density 0.011%

    No Known Activations