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

    Neuronpedia

    INDEX
    Explanations

    doses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eygamber
    -0.07
    、『
    -0.07
    ilis
    -0.06
    ucc
    -0.06
    нин
    -0.06
     Tribune
    -0.06
     прек
    -0.06
     talked
    -0.06
    omination
    -0.06
     Comet
    -0.06
    POSITIVE LOGITS
     fallback
    0.06
     statically
    0.06
     lodging
    0.06
    .query
    0.06
     natives
    0.06
     návr
    0.06
    ishops
    0.06
    clamp
    0.06
     ง
    0.06
    -demand
    0.06
    Act Density 0.008%

    No Known Activations