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

    Neuronpedia

    INDEX
    Explanations

    introduce weakened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usage
    0.51
    $.;
    0.49
    ierto
    0.47
    tLogRow
    0.46
    oua
    0.44
     प्रेरणात्मक
    0.43
    andi
    0.42
    Ouest
    0.42
    上手
    0.42
    appear
    0.42
    POSITIVE LOGITS
     H
    0.48
     Sun
    0.48
     photod
    0.46
     converter
    0.45
     Converter
    0.45
    వ
    0.45
    ரின்
    0.44
     Eks
    0.44
    溦
    0.43
    తున్న
    0.42
    Act Density 0.006%

    No Known Activations