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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ğinden
    -0.06
    Checkpoint
    -0.06
    ため
    -0.06
    opensource
    -0.06
     TWO
    -0.06
    growth
    -0.06
     трохи
    -0.06
    pear
    -0.06
     넘
    -0.06
     جهان
    -0.06
    POSITIVE LOGITS
    ’elle
    0.07
    (Text
    0.06
    chluss
    0.06
     hoops
    0.06
    	api
    0.06
     asteroid
    0.06
     كانت
    0.06
     canv
    0.06
     Fortune
    0.06
     fairness
    0.06
    Act Density 0.007%

    No Known Activations