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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     período
    -0.07
     cryptoc
    -0.06
     uplifting
    -0.06
     modular
    -0.06
     komple
    -0.06
    .trans
    -0.06
     Erik
    -0.06
     banc
    -0.06
     iterate
    -0.06
    [G
    -0.06
    POSITIVE LOGITS
    !?
    0.07
     seated
    0.07
    /video
    0.07
    ocking
    0.06
     السلام
    0.06
    editing
    0.06
    raft
    0.06
    <x
    0.06
     radically
    0.06
     reserves
    0.06
    Act Density 0.000%

    No Known Activations