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

    Neuronpedia

    INDEX
    Explanations

    gravity and density

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DVD
    -0.07
     Mobil
    -0.07
    Received
    -0.07
     Kickstarter
    -0.06
    _Q
    -0.06
     urlparse
    -0.06
     ورز
    -0.06
     acknow
    -0.06
    _received
    -0.06
    _embeddings
    -0.06
    POSITIVE LOGITS
    [Index
    0.08
     필요한
    0.07
    技术
    0.07
    [now
    0.06
     ostensibly
    0.06
    _outer
    0.06
     aşam
    0.06
     tac
    0.06
    [vi
    0.06
    )m
    0.06
    Act Density 0.015%

    No Known Activations