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

    Neuronpedia

    INDEX
    Explanations

    information about importance and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Outside
    0.41
     Outside
    0.37
    citations
    0.37
    istent
    0.36
    Loans
    0.36
    тельство
    0.36
     outside
    0.36
     handsome
    0.35
     राजा
    0.35
    тельные
    0.35
    POSITIVE LOGITS
    คาร
    0.40
    ্কর
    0.38
     intelig
    0.38
     eig
    0.37
     admiss
    0.35
    കെ
    0.35
     tủ
    0.35
    dpy
    0.35
    ኖ
    0.35
    னெ
    0.34
    Act Density 0.001%

    No Known Activations