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

    Neuronpedia

    INDEX
    Explanations

    Binding analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    姓
    -0.07
     restrictions
    -0.07
    _fa
    -0.07
     ";
↵
    -0.06
    export
    -0.06
    üğ
    -0.06
    Ps
    -0.06
    есь
    -0.06
     Acting
    -0.06
     `,↵
    -0.06
    POSITIVE LOGITS
    áme
    0.07
    0.06
     майбут
    0.06
    impan
    0.06
    -forward
    0.06
    濃
    0.06
     prosec
    0.06
     počet
    0.06
     bart
    0.06
    兄弟
    0.06
    Act Density 0.033%

    No Known Activations