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
     matchmaking
    -0.06
     Names
    -0.06
    DAQ
    -0.06
     corres
    -0.06
    .choose
    -0.06
    Button
    -0.06
    	code
    -0.06
    errmsg
    -0.05
     cadre
    -0.05
    asted
    -0.05
    POSITIVE LOGITS
     inherited
    0.07
    を
    0.07
    ]][
    0.06
    ~~
    0.06
     मतलब
    0.06
     cruz
    0.06
    .ins
    0.06
    泡
    0.06
     polo
    0.06
    �i
    0.06
    Act Density 0.010%

    No Known Activations