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

    Neuronpedia

    INDEX
    Explanations

    section headers and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ர்களையும்
    0.27
    ຢູ່ໃນ
    0.25
    <unused2013>
    0.25
    ன்களை
    0.25
    తులను
    0.24
    করিয়
    0.24
    NOMBRE
    0.24
     soltanto
    0.23
    .');
    0.23
    竰
    0.23
    POSITIVE LOGITS
     &
    0.50
    :
    0.47
    :**
    0.40
     -
    0.39
     vs
    0.38
     |
    0.38
     –
    0.36
     /
    0.36
     Explained
    0.35
    ):
    0.35
    Act Density 2.347%

    No Known Activations