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

    Neuronpedia

    INDEX
    Explanations

    iOS development and technical topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंबी
    0.40
     äußerst
    0.40
     braiding
    0.39
     општи
    0.39
    顧
    0.39
    顾
    0.38
    ühle
    0.37
    Sadly
    0.36
    ంటీ
    0.36
     incredibly
    0.36
    POSITIVE LOGITS
     bring
    0.41
     leader
    0.41
    LAS
    0.40
     Necessary
    0.40
     whisper
    0.40
    Ne
    0.39
     gă
    0.38
    Necessary
    0.38
    ([
    0.38
     Ne
    0.37
    Act Density 0.001%

    No Known Activations