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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Km
    -0.07
    Nh
    -0.07
    panion
    -0.06
    _events
    -0.06
    tes
    -0.06
    Interpreter
    -0.06
    Presence
    -0.06
     Gale
    -0.06
    他們
    -0.06
    ptic
    -0.06
    POSITIVE LOGITS
     alike
    0.07
    misc
    0.06
    (diff
    0.06
    recommend
    0.06
    今日
    0.06
     apl
    0.06
     erm
    0.06
     jour
    0.06
     dlg
    0.06
     біл
    0.06
    Act Density 0.030%

    No Known Activations