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

    Neuronpedia

    INDEX
    Explanations

    AI training, integration, compatible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2121>
    0.43
    <unused1741>
    0.42
    <unused425>
    0.42
    <unused710>
    0.39
    被人
    0.39
    FilesIn
    0.38
    <unused301>
    0.38
    <unused2007>
    0.37
    <unused689>
    0.37
    <unused2183>
    0.37
    POSITIVE LOGITS
     centric
    0.40
     சார்பில்
    0.38
    ගේ
    0.38
     bessere
    0.38
     কর্তৃক
    0.38
     favoritas
    0.38
     الجديد
    0.37
    向け
    0.37
     stesso
    0.37
     justement
    0.37
    Act Density 0.053%

    No Known Activations