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

    Neuronpedia

    INDEX
    Explanations

    sleeping in/on spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ex
    -0.07
     reshape
    -0.07
    .writeHead
    -0.07
     Jer
    -0.07
    _engine
    -0.06
    Jer
    -0.06
     dw
    -0.06
    _reply
    -0.06
     CGSizeMake
    -0.06
     облі
    -0.06
    POSITIVE LOGITS
    ]]>
    0.08
    542
    0.07
    าล
    0.07
     muối
    0.06
     sont
    0.06
    uzzi
    0.06
    .bank
    0.06
     Conc
    0.06
    ขาย
    0.06
    .receiver
    0.06
    Act Density 0.015%

    No Known Activations