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

    Neuronpedia

    INDEX
    Explanations

    final answer:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ejected
    0.40
     Provost
    0.40
    Strom
    0.40
    CMI
    0.39
     नाराज
    0.38
     उठाते
    0.37
     Out
    0.37
     removed
    0.37
     Off
    0.37
     الدم
    0.37
    POSITIVE LOGITS
     Greatest
    0.39
    itteln
    0.38
     greatest
    0.37
     bloss
    0.35
    льзова
    0.34
     malo
    0.34
    wikk
    0.34
     sott
    0.33
    awanda
    0.33
    jml
    0.33
    Act Density 0.001%

    No Known Activations