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

    Neuronpedia

    INDEX
    Explanations

    rid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Actions
    -0.07
     joints
    -0.06
     little
    -0.06
    [$_
    -0.06
     circle
    -0.06
     thankful
    -0.06
     तब
    -0.06
     Documentary
    -0.06
     yukarı
    -0.06
     Covent
    -0.06
    POSITIVE LOGITS
     avatar
    0.07
    UGHT
    0.07
     Pied
    0.06
    \Db
    0.06
    iliation
    0.06
    ukkit
    0.06
     RL
    0.06
    blk
    0.06
    'aff
    0.06
    	RTLR
    0.06
    Act Density 0.003%

    No Known Activations