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

    Neuronpedia

    INDEX
    Explanations

    Release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trick
    -0.07
     systematic
    -0.07
     hott
    -0.06
     sécurité
    -0.06
     دع
    -0.06
    Sky
    -0.06
    куль
    -0.06
    ister
    -0.06
    ﾆﾆﾆﾆ
    -0.06
     การแข
    -0.06
    POSITIVE LOGITS
    dll
    0.07
    ималь
    0.06
     dejar
    0.06
    /th
    0.06
    spread
    0.06
     weap
    0.06
     procrast
    0.06
    Really
    0.06
    	web
    0.06
    wives
    0.06
    Act Density 0.001%

    No Known Activations