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

    Neuronpedia

    INDEX
    Explanations

    documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    本セット
    0.41
     Hyde
    0.41
     polypes
    0.41
     organisation
    0.40
    stimulated
    0.39
    StringType
    0.39
    లె
    0.38
     attentively
    0.38
    ampl
    0.37
    subprocess
    0.37
    POSITIVE LOGITS
     remarks
    0.88
    remarks
    0.82
     Remarks
    0.78
    Remarks
    0.74
     comments
    0.68
     <
    0.64
     summary
    0.62
    Comments
    0.61
     COMMENTS
    0.61
     Comments
    0.61
    Act Density 0.003%

    No Known Activations