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

    Neuronpedia

    INDEX
    Explanations

    Flags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    starter
    -0.06
    リン
    -0.06
     ocas
    -0.06
    _WE
    -0.06
    �
    -0.06
    梨
    -0.06
    ين
    -0.06
    Dest
    -0.06
    (im
    -0.06
    ραν
    -0.06
    POSITIVE LOGITS
    .Management
    0.08
    Flags
    0.07
     designated
    0.07
     Unified
    0.06
    ONGLONG
    0.06
     signifies
    0.06
     Raise
    0.06
    >equals
    0.06
    .compare
    0.06
    .ToDouble
    0.06
    Act Density 0.001%

    No Known Activations