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

    Neuronpedia

    INDEX
    Explanations

    Voyage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shuffle
    -0.08
     Du
    -0.07
     fulfil
    -0.06
    روم
    -0.06
    TXT
    -0.06
    保驾护航
    -0.06
    但
    -0.06
    上级
    -0.06
    Tony
    -0.06
     wn
    -0.06
    POSITIVE LOGITS
    finding
    0.08
    (video
    0.08
    thumbnails
    0.07
     voyage
    0.07
     learns
    0.07
    -copy
    0.07
     adaptive
    0.07
    esting
    0.07
    acionales
    0.07
     Watts
    0.07
    Act Density 0.007%

    No Known Activations