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

    Neuronpedia

    INDEX
    Explanations

    increasing by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    2.11
    .].
    1.98
    ].
    1.92
    .).
    1.77
     from
    1.76
    ↵↵
    1.75
    。
    1.74
    ).
    1.72
    .]
    1.71
    .\
    1.71
    POSITIVE LOGITS
     thì
    1.28
     则
    1.26
     entonces
    1.18
    이라면
    1.18
     τότε
    1.15
    chtigt
    1.14
    ?..
    1.10
    "?:
    1.08
     vẫn
    1.07
    ANCEL
    1.06
    Act Density 0.423%

    No Known Activations