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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Server
    -0.07
    (mode
    -0.07
     Fall
    -0.07
    Generic
    -0.06
     Sat
    -0.06
    Av
    -0.06
     �
    -0.06
     Sid
    -0.06
    的人
    -0.06
     Four
    -0.06
    POSITIVE LOGITS
     ferry
    0.07
     lul
    0.07
    ushman
    0.06
     münchen
    0.06
     commande
    0.06
    PLL
    0.06
    _SECRET
    0.06
     nonatomic
    0.06
     Taipei
    0.06
    ทำ
    0.06
    Act Density 0.010%

    No Known Activations