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

    Neuronpedia

    INDEX
    Explanations

    including

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verschiedenen
    -0.07
     जह
    -0.06
     �
    -0.06
     plaza
    -0.06
    spath
    -0.06
    EMPL
    -0.06
     ハ
    -0.06
    iment
    -0.06
     percept
    -0.06
    zzarella
    -0.06
    POSITIVE LOGITS
     анти
    0.07
    /loading
    0.07
     Miz
    0.06
     끝
    0.06
     ops
    0.06
     discrepancies
    0.06
     dys
    0.06
     Bil
    0.06
     جديد
    0.06
    luğu
    0.06
    Act Density 0.028%

    No Known Activations