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

    Neuronpedia

    INDEX
    Explanations

    showcasing feline, actions are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সম্মিল
    0.44
     المالية
    0.44
     problèmes
    0.42
     ঢাকায়
    0.42
     informática
    0.41
     €,
    0.41
    赵
    0.40
     subwoofer
    0.40
    ,​
    0.40
     खेलते
    0.39
    POSITIVE LOGITS
    細
    0.44
    ename
    0.42
    Joining
    0.42
    fds
    0.42
    দন
    0.42
    ahal
    0.41
    anjang
    0.40
    esz
    0.39
    as
    0.38
    YH
    0.38
    Act Density 0.002%

    No Known Activations