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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _minor
    -0.07
     Latitude
    -0.06
    ypical
    -0.06
     reconnect
    -0.06
     служби
    -0.06
    Latin
    -0.06
     decrypt
    -0.06
    _tw
    -0.06
    .LEFT
    -0.06
     stav
    -0.06
    POSITIVE LOGITS
     pornost
    0.07
     Dare
    0.07
    овано
    0.07
     rins
    0.06
    ังก
    0.06
    unan
    0.06
    alarına
    0.06
    ařilo
    0.06
     sure
    0.06
     borç
    0.06
    Act Density 0.033%

    No Known Activations