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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    १�
    -0.08
    egers
    -0.06
    ffic
    -0.06
    ifth
    -0.06
    ris
    -0.06
    ак
    -0.06
    OURCE
    -0.06
    PLIC
    -0.06
    _Name
    -0.06
     ReadOnly
    -0.06
    POSITIVE LOGITS
    自治
    0.07
     Somebody
    0.07
     может
    0.07
    :]↵↵
    0.07
     Blogger
    0.06
    سة
    0.06
    .interface
    0.06
     NTN
    0.06
    ([↵
    0.06
     SMA
    0.06
    Act Density 0.001%

    No Known Activations