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

    Neuronpedia

    INDEX
    Explanations

    special characters and unicode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whispered
    0.41
    '
    0.39
    iza
    0.38
     أن
    0.38
    ല്ലോ
    0.38
     obwohl
    0.38
    ’
    0.37
     நான்
    0.36
     whispers
    0.36
    да
    0.36
    POSITIVE LOGITS
    A
    0.51
    S
    0.47
     महोत्सव
    0.44
    In
    0.43
    projekt
    0.43
     į
    0.42
    াজের
    0.41
    Element
    0.40
    க்கப்படுகிறது
    0.40
    their
    0.40
    Act Density 0.004%

    No Known Activations