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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apol
    -0.07
     epic
    -0.06
     alliance
    -0.06
    ACC
    -0.06
    DE
    -0.06
    .setPosition
    -0.06
     Fairfax
    -0.06
     Pad
    -0.06
     Pap
    -0.06
    .Sp
    -0.06
    POSITIVE LOGITS
    ٬
    0.07
     العالمية
    0.07
    출장안마
    0.06
     περισσότε
    0.06
    	Date
    0.06
    >User
    0.06
    Notes
    0.06
     eher
    0.06
    correct
    0.06
    특
    0.06
    Act Density 0.002%

    No Known Activations