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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =";↵
    -0.07
     проте
    -0.07
     indef
    -0.06
    ozilla
    -0.06
    ською
    -0.06
    JEXEC
    -0.06
    це
    -0.06
    msgs
    -0.06
     Pg
    -0.06
    ="../
    -0.06
    POSITIVE LOGITS
     shielding
    0.07
     announces
    0.07
     gardening
    0.07
     joining
    0.07
     brace
    0.06
    илась
    0.06
     appear
    0.06
     pair
    0.06
     trimmed
    0.06
    leader
    0.06
    Act Density 0.000%

    No Known Activations