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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ra
    -0.06
     mot
    -0.06
    @property
    -0.06
     Tor
    -0.06
     tvoř
    -0.06
     clips
    -0.06
    .Rendering
    -0.06
    ips
    -0.06
     oltre
    -0.06
     Surf
    -0.06
    POSITIVE LOGITS
    .initialize
    0.07
    egasus
    0.07
     methane
    0.07
    _bc
    0.06
    abajo
    0.06
     medial
    0.06
    '-
    0.06
    时
    0.06
     oversized
    0.06
    IsNull
    0.06
    Act Density 0.000%

    No Known Activations