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

    Neuronpedia

    INDEX
    Explanations

    initiate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    歲
    -0.08
    (cx
    -0.08
    xFFF
    -0.08
    TextColor
    -0.07
    Ề
    -0.07
     ll
    -0.07
    ede
    -0.07
    :NO
    -0.07
    Tes
    -0.07
     sóc
    -0.07
    POSITIVE LOGITS
     initiated
    0.08
     delayed
    0.08
     Artifact
    0.07
    مناق
    0.07
    .FileSystem
    0.07
    に入った
    0.07
    /ayushman
    0.07
    ᾰ
    0.07
     United
    0.07
     papers
    0.07
    Act Density 0.012%

    No Known Activations