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

    Neuronpedia

    INDEX
    Explanations

    planets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allot
    -0.07
    _ori
    -0.07
     PRI
    -0.07
    iles
    -0.07
    나
    -0.07
    iid
    -0.07
    èle
    -0.07
     lace
    -0.06
     Est
    -0.06
     toast
    -0.06
    POSITIVE LOGITS
    .button
    0.08
    /world
    0.07
     początk
    0.07
     Effects
    0.07
    難
    0.07
     dropdown
    0.07
    :before
    0.06
     viewport
    0.06
    娑
    0.06
    _seen
    0.06
    Act Density 0.006%

    No Known Activations