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

    Neuronpedia

    INDEX
    Explanations

    handle click submit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yapı
    0.44
    ϝ
    0.40
    <0xF0>
    0.40
    ް
    0.40
     Conta
    0.39
     invari
    0.39
    你不
    0.38
     ያሉ
    0.38
     அல்லாஹ்
    0.38
     powinno
    0.38
    POSITIVE LOGITS
    go
    0.52
    click
    0.49
     click
    0.45
     Click
    0.44
    clickHandler
    0.44
    Click
    0.43
    CLICK
    0.42
     clicked
    0.41
    handleClick
    0.41
     decline
    0.41
    Act Density 0.019%

    No Known Activations