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

    Neuronpedia

    INDEX
    Explanations

    heard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تعديل
    -0.07
    omanip
    -0.07
    loating
    -0.07
     كمية
    -0.07
    Sto
    -0.07
     গুরু
    -0.07
    _Save
    -0.07
     remarque
    -0.07
     sanctuary
    -0.07
     Tomorrow
    -0.07
    POSITIVE LOGITS
     familiarity
    0.14
     Familiar
    0.12
    知
    0.12
    amiliar
    0.12
     familiarize
    0.11
     acquaint
    0.11
     familiar
    0.11
     kennt
    0.10
     connaissent
    0.10
     അറിയ
    0.10
    Act Density 0.086%

    No Known Activations