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

    Neuronpedia

    INDEX
    Explanations

    need input or facing issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     methyl
    0.44
     methylated
    0.40
     mysql
    0.40
     assess
    0.38
     socialization
    0.38
     JUAN
    0.37
     youtube
    0.37
    SHALL
    0.36
     optar
    0.35
     terres
    0.35
    POSITIVE LOGITS
     Otherwise
    0.52
    Deadline
    0.46
    Hundreds
    0.46
    Otherwise
    0.44
     Failing
    0.44
     Deadline
    0.43
    ข้อมูล
    0.42
     Hundreds
    0.41
    できない
    0.39
     Missing
    0.39
    Act Density 0.163%

    No Known Activations