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

    Neuronpedia

    INDEX
    Explanations

    completion or past state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blockchain
    -0.07
     亚
    -0.06
    asured
    -0.06
    hs
    -0.06
    same
    -0.06
    matrix
    -0.06
     Data
    -0.06
     Cort
    -0.06
     fashioned
    -0.06
    Overlap
    -0.06
    POSITIVE LOGITS
    Pu
    0.07
    %@",
    0.06
     झ
    0.06
    issional
    0.06
     (!_
    0.06
    nants
    0.06
    CALL
    0.06
     })).
    0.06
    ={!
    0.06
    著
    0.06
    Act Density 0.098%

    No Known Activations