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

    Neuronpedia

    INDEX
    Explanations

    architecture descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hat
    -0.06
    _ln
    -0.06
    「你
    -0.06
     feat
    -0.06
    Firefox
    -0.06
     Exped
    -0.06
     firefox
    -0.06
    _pes
    -0.06
    alue
    -0.06
     đẩy
    -0.06
    POSITIVE LOGITS
     Gon
    0.07
     ery
    0.06
    stantial
    0.06
    baby
    0.06
     Candid
    0.06
    asthan
    0.06
    Demon
    0.06
    vertime
    0.06
     exceptionally
    0.06
    thon
    0.06
    Act Density 0.008%

    No Known Activations