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
     or
    -0.07
    pectral
    -0.07
    	or
    -0.06
    kah
    -0.06
     Zoo
    -0.06
     formats
    -0.06
     BALL
    -0.06
     bounce
    -0.06
     Chính
    -0.06
    Bound
    -0.06
    POSITIVE LOGITS
     matrimon
    0.06
    phet
    0.06
    министра
    0.06
     اح
    0.06
    ็
    0.06
    igmat
    0.06
    ama
    0.06
    .getBody
    0.06
    ız
    0.06
     Lands
    0.06
    Act Density 0.001%

    No Known Activations