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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saturn
    -0.07
    êtes
    -0.07
    ALI
    -0.06
    .top
    -0.06
    MX
    -0.06
    KY
    -0.06
    ￣｀
    -0.06
     positives
    -0.06
    زان
    -0.06
     Theater
    -0.06
    POSITIVE LOGITS
    Registers
    0.07
     nhà
    0.07
     vết
    0.06
     ::
    0.06
    还
    0.06
    Guess
    0.06
    _cliente
    0.06
    み
    0.06
    .hs
    0.06
     अम
    0.06
    Act Density 0.002%

    No Known Activations