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

    Neuronpedia

    INDEX
    Explanations

    dough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betray
    -0.07
    Exchange
    -0.07
    XR
    -0.07
    Inst
    -0.07
    CEED
    -0.07
     cerr
    -0.07
    've
    -0.07
    _re
    -0.07
    "c
    -0.07
    urchase
    -0.06
    POSITIVE LOGITS
     dough
    0.08
    Expiration
    0.07
    솜
    0.07
     Erie
    0.07
    ohana
    0.07
    ホーム
    0.07
     процед
    0.07
    وها
    0.07
    raison
    0.07
    opathic
    0.07
    Act Density 0.002%

    No Known Activations