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

    Neuronpedia

    INDEX
    Explanations

    code and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тьми
    0.37
     beziehen
    0.36
     пять
    0.35
     دارم
    0.35
     حذف
    0.35
    𝒃
    0.35
    맇
    0.34
    ๗
    0.34
    fifths
    0.33
    妈
    0.33
    POSITIVE LOGITS
    Scanner
    0.38
    tered
    0.37
    ZERO
    0.37
     inflation
    0.36
     psi
    0.36
    Information
    0.35
     Schra
    0.35
    Dit
    0.34
     صدي
    0.34
    itu
    0.34
    Act Density 0.005%

    No Known Activations