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

    Neuronpedia

    INDEX
    Explanations

    bidirectional context training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     주로
    0.44
    MRI
    0.43
    مون
    0.41
    沇
    0.41
     principalement
    0.40
    Mexico
    0.40
    ुअल
    0.40
    Loops
    0.40
    و
    0.40
    وبات
    0.40
    POSITIVE LOGITS
    ivo
    0.38
    óra
    0.38
    pathetic
    0.38
     confided
    0.37
    am
    0.36
    rée
    0.36
    赜
    0.36
    nyi
    0.36
    ૃત
    0.36
     Stanley
    0.35
    Act Density 0.001%

    No Known Activations