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

    Neuronpedia

    INDEX
    Explanations

    sincere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    john
    -0.07
     enjoyment
    -0.07
    (":
    -0.07
    erview
    -0.07
    -forward
    -0.07
     Teddy
    -0.07
     Assets
    -0.07
     EVAL
    -0.07
    owers
    -0.07
    fox
    -0.07
    POSITIVE LOGITS
     didn
    0.07
     значительно
    0.07
    끕
    0.07
     ويم
    0.07
    =>{↵
    0.06
    ReadWrite
    0.06
    нач
    0.06
     table
    0.06
    :UIControlState
    0.06
     produced
    0.06
    Act Density 0.002%

    No Known Activations