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

    Neuronpedia

    INDEX
    Explanations

    I'm/am/are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _special
    -0.07
    く
    -0.06
    _shapes
    -0.06
    武
    -0.06
    305
    -0.06
    burgh
    -0.06
    ните
    -0.06
    help
    -0.06
     tema
    -0.05
    _fragment
    -0.05
    POSITIVE LOGITS
    _experience
    0.07
    琳
    0.07
    戒
    0.07
     TL
    0.07
     coraz
    0.07
     ikt
    0.06
     resident
    0.06
    اوت
    0.06
     centrif
    0.06
     kancel
    0.06
    Act Density 0.035%

    No Known Activations