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

    Neuronpedia

    INDEX
    Explanations

    evaluates to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গিয়েছিল
    0.43
     গিয়েছিলেন
    0.40
    %}
    0.39
    jahter
    0.39
    שת
    0.38
    ことが多い
    0.38
     multiplicado
    0.38
     দিয়েছিলেন
    0.37
    䂘
    0.35
    ;')
    0.35
    POSITIVE LOGITS
     =
    1.36
    =
    1.24
    ＝
    0.96
    >=</
    0.94
    =\
    0.92
     $=
    0.90
    }=
    0.87
     $=$
    0.86
    0.85
    )=
    0.84
    Act Density 0.036%

    No Known Activations