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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TOR
    -0.07
    λος
    -0.07
    áy
    -0.06
    姊
    -0.06
    fait
    -0.06
    atial
    -0.06
    .TO
    -0.06
    τικός
    -0.06
     vandalism
    -0.06
    .Flush
    -0.06
    POSITIVE LOGITS
     coupe
    0.07
    _Tr
    0.06
    (RE
    0.06
     facilitates
    0.06
    \",\"
    0.06
     rog
    0.06
     nuestras
    0.06
     Decre
    0.06
    	REG
    0.06
    .makedirs
    0.06
    Act Density 0.035%

    No Known Activations