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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Matter
    -0.07
    tool
    -0.07
    both
    -0.07
    wor
    -0.07
     matter
    -0.06
    recommend
    -0.06
    幼
    -0.06
    ático
    -0.06
    mtx
    -0.06
     fool
    -0.06
    POSITIVE LOGITS
    (dirname
    0.07
     Gre
    0.07
     innovation
    0.06
     Deg
    0.06
    ΕΣ
    0.06
     didSelect
    0.06
     pleasant
    0.06
     -*
    0.06
    abytes
    0.06
     veget
    0.06
    Act Density 0.285%

    No Known Activations