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

    Neuronpedia

    INDEX
    Explanations

    providing context or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.44
    *.
    0.40
    .
    0.37
    ’.
    0.36
    ®.
    0.35
     کی۔
    0.35
    。
    0.35
    .*
    0.34
    ™.
    0.34
    ۔
    0.33
    POSITIVE LOGITS
    ிருப்பது
    0.39
     zorgt
    0.38
     allows
    0.34
     एखा
    0.34
     позволяет
    0.33
     isn
    0.32
    ತೆಯ
    0.32
     is
    0.32
     является
    0.31
     ilyen
    0.31
    Act Density 0.594%

    No Known Activations