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

    Neuronpedia

    INDEX
    Explanations

    names/identities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attained
    -0.07
    -machine
    -0.07
    xygen
    -0.07
     oxy
    -0.07
     microbial
    -0.07
     히
    -0.07
     precip
    -0.07
    _course
    -0.06
     삭제
    -0.06
     مه
    -0.06
    POSITIVE LOGITS
    (digits
    0.07
    ernal
    0.06
    �
    0.06
    >NN
    0.06
    	NS
    0.06
     invariably
    0.06
    νηση
    0.06
    (down
    0.05
    (resp
    0.05
     then
    0.05
    Act Density 0.146%

    No Known Activations