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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _defs
    -0.07
    .async
    -0.07
    .generate
    -0.07
     Ninja
    -0.07
    .avi
    -0.06
     Fischer
    -0.06
     coma
    -0.06
    .Up
    -0.06
    Comparer
    -0.06
    .mapper
    -0.06
    POSITIVE LOGITS
    蛇
    0.07
     Hartford
    0.07
     без
    0.06
     pacman
    0.06
    inceton
    0.06
    _NONNULL
    0.06
    ologne
    0.06
    stanbul
    0.06
    (script
    0.06
     bezier
    0.06
    Act Density 0.010%

    No Known Activations