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

    Neuronpedia

    INDEX
    Explanations

    created or required for a purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     考え
    0.45
     үз
    0.44
    的方法
    0.42
    0.42
    0.42
     provoke
    0.41
    嘮
    0.41
    DefinitionGroup
    0.41
     بعد
    0.41
    ៖
    0.40
    POSITIVE LOGITS
    b
    0.55
    c
    0.47
     animals
    0.45
     animais
    0.44
     animale
    0.44
    to
    0.44
     Tanks
    0.44
    বি
    0.43
    m
    0.43
     abitanti
    0.42
    Act Density 0.013%

    No Known Activations