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

    Neuronpedia

    INDEX
    Explanations

    <table>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glean
    -0.07
    (Handle
    -0.07
     unanimous
    -0.07
    갓
    -0.07
     unseen
    -0.07
    .Replace
    -0.07
     gia
    -0.07
    隐蔽
    -0.07
     이
    -0.07
     Amazing
    -0.06
    POSITIVE LOGITS
    _UPPER
    0.08
    INPUT
    0.07
    ayaran
    0.07
    涉足
    0.07
    _PROC
    0.07
    aviors
    0.07
    Relation
    0.07
     результат
    0.07
    しようと
    0.06
    制定了
    0.06
    Act Density 0.002%

    No Known Activations