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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments / code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     operates
    0.57
     bouche
    0.56
    क्रोस
    0.55
    icion
    0.54
    彩
    0.52
    ченных
    0.51
     provoz
    0.50
     fails
    0.50
     പതി
    0.50
     integrates
    0.49
    POSITIVE LOGITS
     Kwan
    0.54
    んにちは
    0.53
     Whose
    0.52
    大人
    0.49
     Moving
    0.49
     Uma
    0.48
     Alan
    0.48
     Marble
    0.47
    റില്‍
    0.47
     Jelly
    0.47
    Act Density 0.000%

    No Known Activations