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

    Neuronpedia

    INDEX
    Explanations

    say ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iyi
    -0.07
    TypeEnum
    -0.07
    python
    -0.06
    	ERROR
    -0.06
    	bs
    -0.06
    -phone
    -0.06
     手
    -0.06
    _objs
    -0.06
     survived
    -0.06
     geçir
    -0.06
    POSITIVE LOGITS
     storing
    0.06
    _MORE
    0.06
     populated
    0.06
     plagiar
    0.06
    관리자
    0.06
    ियर
    0.06
    >ID
    0.06
     applicable
    0.06
    Sele
    0.06
    ัศน
    0.06
    Act Density 0.006%

    No Known Activations