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

    Neuronpedia

    INDEX
    Explanations

    multi-factor authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viz
    0.61
    LIK
    0.58
     indi
    0.58
     lampe
    0.55
     خار
    0.55
     gimnas
    0.54
    苹
    0.53
     grim
    0.53
     horr
    0.52
     Viz
    0.52
    POSITIVE LOGITS
    ⁠
    0.58
    <0xCD>
    0.53
    ‎
    0.52
    </u>
    0.50
    <0xF4>
    0.48
    <h6>
    0.47
    ��������
    0.47
    ;
    0.47
    ʺ
    0.47
    ‐
    0.45
    Act Density 0.519%

    No Known Activations