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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     REL
    -0.06
     rom
    -0.06
    ัน
    -0.06
     nt
    -0.06
    _assoc
    -0.06
     dictated
    -0.06
     PTS
    -0.06
     Paste
    -0.06
    EVER
    -0.06
    렸다
    -0.06
    POSITIVE LOGITS
     measurements
    0.07
     housed
    0.07
    .booking
    0.07
    successful
    0.07
    (skill
    0.06
     synchronization
    0.06
    _Link
    0.06
    /thread
    0.06
     toxicity
    0.06
     synchronized
    0.06
    Act Density 0.000%

    No Known Activations