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

    Neuronpedia

    INDEX
    Explanations

    to set if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     POLIT
    -0.07
     deadliest
    -0.06
     Athen
    -0.06
     şu
    -0.06
    شم
    -0.06
     PURPOSE
    -0.06
     Tulsa
    -0.06
    ZO
    -0.06
    .getEntity
    -0.06
     kişilerin
    -0.06
    POSITIVE LOGITS
    σία
    0.07
    views
    0.06
     upgraded
    0.06
    산업
    0.06
    Enabled
    0.06
    /releases
    0.06
    -warning
    0.06
    	net
    0.06
     music
    0.06
    	assertFalse
    0.06
    Act Density 0.004%

    No Known Activations