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

    Neuronpedia

    INDEX
    Explanations

    code structure and function arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ける
    0.45
    ંત્રણ
    0.44
    ול
    0.44
    ниця
    0.43
    োলার
    0.42
    нице
    0.42
    constraintStart
    0.42
    தாய
    0.42
    OPA
    0.41
    寳
    0.41
    POSITIVE LOGITS
     ​​
    0.45
     Wol
    0.44
     साल
    0.44
     संचार
    0.44
    ordnet
    0.43
     रिसर्च
    0.43
     de
    0.43
     थोड़ा
    0.43
     अन्
    0.43
    larından
    0.42
    Act Density 0.067%

    No Known Activations