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
    ают
    -0.07
     Soap
    -0.07
    TMP
    -0.06
    _H
    -0.06
     soap
    -0.06
     dragged
    -0.06
    ải
    -0.06
    saldo
    -0.06
     sớm
    -0.06
     recap
    -0.06
    POSITIVE LOGITS
    jb
    0.07
    ★★
    0.07
     FILTER
    0.06
     М
    0.06
    >>&
    0.06
    جي
    0.06
    ?}",
    0.06
    طع
    0.06
    ünchen
    0.06
     viewpoint
    0.06
    Act Density 0.039%

    No Known Activations