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

    Neuronpedia

    INDEX
    Explanations

    technical field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    paired
    -0.07
    trial
    -0.07
    ident
    -0.07
     хоча
    -0.07
    folio
    -0.07
    Indented
    -0.06
    stitutions
    -0.06
     бо
    -0.06
     notes
    -0.06
    (ERROR
    -0.06
    POSITIVE LOGITS
     dumpster
    0.07
    HCI
    0.07
     aplic
    0.06
     臺
    0.06
    ’↵
    0.06
     الجز
    0.06
    orp
    0.06
     jumped
    0.06
     yıldız
    0.06
    Forgot
    0.06
    Act Density 0.001%

    No Known Activations