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

    Neuronpedia

    INDEX
    Explanations

    Code, JSON, or API definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lens
    -0.07
     backwards
    -0.06
    暾
    -0.06
    ḅ
    -0.06
     heel
    -0.06
    ᱚ
    -0.06
    $order
    -0.06
    亿万
    -0.06
    瘩
    -0.06
    🏃
    -0.06
    POSITIVE LOGITS
    _tab
    0.07
     Hope
    0.07
    믜
    0.07
     فكرة
    0.07
    ighthouse
    0.06
    ichever
    0.06
    UPI
    0.06
     __________________
    0.06
     tránh
    0.06
    Constraints
    0.06
    Act Density 0.004%

    No Known Activations