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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )`;
    0.43
    󰡕
    0.40
     hijab
    0.40
    ྀ
    0.38
    잭
    0.38
    cdZ
    0.37
     होती
    0.36
    ׳
    0.36
    ']),
    0.35
    COMANDA
    0.35
    POSITIVE LOGITS
    }\
    0.66
    }%
    0.54
     {}\
    0.51
    {\
    0.50
    }{\
    0.48
    }}\
    0.47
    )\
    0.47
     \
    0.47
    }{}
    0.47
    <\
    0.46
    Act Density 0.006%

    No Known Activations