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

    Neuronpedia

    INDEX
    Explanations

    code method access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }+
    0.48
    素晴
    0.45
     Antônio
    0.44
     CustB
    0.44
     स्थानांतर
    0.41
     मैथमेटिक्स
    0.41
    𒇷
    0.41
    獬
    0.41
     Ávila
    0.40
     সরাস
    0.40
    POSITIVE LOGITS
    ().
    0.68
    .
    0.65
    ._
    0.55
    _.
    0.52
    _
    0.52
    /*.
    0.51
    ->
    0.50
    ::
    0.50
    。
    0.50
    ?.
    0.46
    Act Density 0.178%

    No Known Activations