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

    Neuronpedia

    INDEX
    Explanations

    higher numbers or priority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    লাষ
    0.50
     storing
    0.49
     getContentPane
    0.47
     灯
    0.47
     UNNEEDED
    0.46
    धनों
    0.46
     继续
    0.45
     টাকার
    0.45
    )}]
    0.45
    dürü
    0.44
    POSITIVE LOGITS
    al
    0.48
     Pfl
    0.46
    isola
    0.46
     N
    0.45
     Zel
    0.45
     Psic
    0.45
     piace
    0.45
     Z
    0.44
     Fau
    0.44
     Princ
    0.44
    Act Density 0.001%

    No Known Activations