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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONFIRM
    -0.08
    .ob
    -0.08
    dden
    -0.07
    caa
    -0.07
    OFFSET
    -0.07
    defines
    -0.07
    .Caption
    -0.07
    IFA
    -0.07
    Score
    -0.07
    /exp
    -0.07
    POSITIVE LOGITS
     precedent
    0.07
    产品经理
    0.07
    Ậ
    0.06
    isecond
    0.06
    不完
    0.06
     Neptune
    0.06
     nicht
    0.06
    等
    0.06
     Delaware
    0.06
    ]');↵
    0.06
    Act Density 0.042%

    No Known Activations