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

    Neuronpedia

    INDEX
    Explanations

    SMART goals' Relevant component

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يريا
    0.41
     সিদ্ধ
    0.40
    axios
    0.39
     immobilized
    0.39
     Yii
    0.38
    सुम
    0.38
     género
    0.38
    emeinschaft
    0.38
     nari
    0.37
     punishable
    0.37
    POSITIVE LOGITS
     ramp
    0.39
    clen
    0.38
    PLO
    0.38
    PQ
    0.38
    XL
    0.37
    Reg
    0.37
     PQ
    0.37
    nego
    0.37
    פק
    0.36
     PBL
    0.36
    Act Density 0.000%

    No Known Activations