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

    Neuronpedia

    INDEX
    Explanations

    requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loans
    -0.07
    מחלה
    -0.07
    .part
    -0.07
    VectorXd
    -0.07
    AuthService
    -0.06
     الفنان
    -0.06
    Moment
    -0.06
    ,:);↵
    -0.06
    แนะ
    -0.06
    뾰
    -0.06
    POSITIVE LOGITS
    �
    0.08
     MAG
    0.07
    축
    0.07
    多种
    0.07
    패
    0.07
     bars
    0.06
     II
    0.06
    ज
    0.06
    .ir
    0.06
    주
    0.06
    Act Density 0.183%

    No Known Activations