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

    Neuronpedia

    INDEX
    Explanations

    language diversity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ㅛ
    0.41
     thisStudent
    0.38
    <unused2169>
    0.37
    året
    0.37
    錒
    0.37
    <unused2125>
    0.37
    TGFuZ
    0.36
    pInBuffer
    0.36
    ComponentScan
    0.35
     BasicContainer
    0.35
    POSITIVE LOGITS
    he
    0.42
    Y
    0.40
    we
    0.39
    at
    0.39
     No
    0.39
    ف
    0.39
    -
    0.38
     we
    0.38
    se
    0.38
    to
    0.37
    Act Density 0.054%

    No Known Activations