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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dhcp
    -0.07
     누구
    -0.07
    .Deep
    -0.07
     何
    -0.07
     Hint
    -0.06
     decreased
    -0.06
    .Con
    -0.06
    .PRO
    -0.06
    .secondary
    -0.06
     선택
    -0.06
    POSITIVE LOGITS
     Gall
    0.18
     gall
    0.16
     Gallagher
    0.10
    Ga
    0.07
     sling
    0.07
    Handle
    0.07
    all
    0.07
    eldon
    0.07
    516
    0.07
    tle
    0.07
    Act Density 0.002%

    No Known Activations