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

    Neuronpedia

    INDEX
    Explanations

    months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     앞으로
    0.21
     waveguide
    0.20
    liques
    0.20
    बाह
    0.20
    <unused4>
    0.20
    ısıyla
    0.19
     zwięks
    0.19
    軞
    0.19
    ारीरिक
    0.19
     geplant
    0.19
    POSITIVE LOGITS
     January
    0.39
    January
    0.33
     December
    0.33
     November
    0.31
     February
    0.31
     September
    0.30
    September
    0.29
     August
    0.29
     October
    0.29
     July
    0.28
    Act Density 0.033%

    No Known Activations