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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setTitle
    -0.07
    Workbook
    -0.06
     Anal
    -0.06
    �
    -0.06
    :@
    -0.06
    ()->
    -0.06
    φυ
    -0.06
    _offset
    -0.06
     TOKEN
    -0.06
    _already
    -0.06
    POSITIVE LOGITS
     barred
    0.07
    vanished
    0.06
     Raqqa
    0.06
    102
    0.06
    obby
    0.06
     дот
    0.06
     kam
    0.06
     frei
    0.06
    exist
    0.06
     vere
    0.06
    Act Density 0.000%

    No Known Activations