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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punches
    -0.07
    .POST
    -0.06
    ovní
    -0.06
     Instructions
    -0.06
    _DOM
    -0.06
     Intro
    -0.06
     endif
    -0.06
    zing
    -0.06
     subcontract
    -0.06
    .Generate
    -0.06
    POSITIVE LOGITS
     can
    0.07
     können
    0.07
     прекрас
    0.06
     może
    0.06
     talent
    0.06
     могут
    0.06
    Psych
    0.06
     PST
    0.06
     lays
    0.06
    0.06
    Act Density 0.007%

    No Known Activations