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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    d
    -0.07
     gubern
    -0.06
    Site
    -0.06
     Amp
    -0.06
     condom
    -0.06
    พวก
    -0.06
     rut
    -0.06
    LEncoder
    -0.06
     terse
    -0.06
    Sr
    -0.06
    POSITIVE LOGITS
    	boost
    0.07
    adb
    0.07
    _reduction
    0.07
     spite
    0.07
    ATES
    0.07
    .Math
    0.07
     MASTER
    0.07
     LOWER
    0.06
    768
    0.06
    hoe
    0.06
    Act Density 0.091%

    No Known Activations