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

    Neuronpedia

    INDEX
    Explanations

    mort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overarching
    -0.07
    =set
    -0.07
     lun
    -0.07
    पी
    -0.07
     reside
    -0.07
     formulate
    -0.07
     [↵
    -0.07
     aspek
    -0.07
    -0.07
     existing
    -0.07
    POSITIVE LOGITS
     unexpectedly
    0.10
     неож
    0.10
     inesper
    0.10
    Unexpected
    0.10
    unexpected
    0.10
     unintended
    0.10
     unforeseen
    0.10
    igkeiten
    0.09
     inadvert
    0.09
     accidentally
    0.09
    Act Density 0.039%
    No Known Activations