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

    Neuronpedia

    INDEX
    Explanations

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hugs
    0.56
     Able
    0.51
    癥
    0.48
     Jobs
    0.48
     outlets
    0.47
     hugging
    0.47
     Realtors
    0.46
     Elke
    0.46
     Erkennt
    0.46
     grads
    0.46
    POSITIVE LOGITS
    isu
    0.56
    ição
    0.55
    imming
    0.54
    ous
    0.52
    isiin
    0.52
    ímica
    0.52
    ế
    0.52
    indungi
    0.52
    uge
    0.51
    िखित
    0.51
    Act Density 0.001%

    No Known Activations