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

    Neuronpedia

    INDEX
    Explanations

    missed one someone will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maz
    0.42
     commemorates
    0.39
     anniversary
    0.39
     refriger
    0.39
     commemorating
    0.38
     Who
    0.38
     SY
    0.38
    ulz
    0.38
     injuries
    0.38
     Maz
    0.37
    POSITIVE LOGITS
     גבוה
    0.44
    ocèle
    0.44
    oMatrix
    0.43
    Avec
    0.42
     '!
    0.42
    QSpacerItem
    0.42
     دهد
    0.41
     varphi
    0.40
    चान
    0.40
    spacePad
    0.40
    Act Density 0.001%

    No Known Activations