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

    Neuronpedia

    INDEX
    Explanations

    relatable experiences

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    _csv
    -0.08
    pożycz
    -0.07
    _interp
    -0.07
     pożycz
    -0.07
    掀起
    -0.07
     prest
    -0.07
     kleinen
    -0.06
    	pw
    -0.06
    ivamente
    -0.06
     pornost
    -0.06
    POSITIVE LOGITS
    tracker
    0.07
     traveller
    0.07
     WIN
    0.07
    发觉
    0.07
     punched
    0.07
     stacking
    0.07
     trapping
    0.07
     Vivo
    0.07
    Assigned
    0.07
    -change
    0.07
    Act Density 0.052%

    No Known Activations