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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruined
    -0.06
    Toy
    -0.06
    мотр
    -0.06
     ово
    -0.06
     isot
    -0.06
     Plants
    -0.06
    UMB
    -0.06
    This
    -0.06
     hydraulic
    -0.06
    _T
    -0.06
    POSITIVE LOGITS
    (inputs
    0.07
    (secret
    0.07
    attendance
    0.06
     doc
    0.06
    (reply
    0.06
    	lp
    0.06
    	exec
    0.06
    	actual
    0.06
     تست
    0.06
    mentor
    0.06
    Act Density 0.000%

    No Known Activations