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

    Neuronpedia

    INDEX
    Explanations

    claim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embedded
    -0.07
    .Xtra
    -0.07
     После
    -0.07
    Refresh
    -0.06
     Kag
    -0.06
     canonical
    -0.06
    department
    -0.06
    .Messages
    -0.06
     Ricky
    -0.06
    oyer
    -0.06
    POSITIVE LOGITS
    ような
    0.07
     xúc
    0.06
     overloaded
    0.06
     จาก
    0.06
    MakeRange
    0.06
     �
    0.06
    _DEST
    0.06
    'était
    0.06
     claim
    0.06
     moc
    0.06
    Act Density 0.013%

    No Known Activations