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

    Neuronpedia

    INDEX
    Explanations

    Fortify Program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Deve
    0.41
    DER
    0.39
    दरम्यान
    0.39
    upné
    0.38
    addAnimation
    0.37
     Happiness
    0.37
    dte
    0.36
     Recognize
    0.36
    nota
    0.36
     Getter
    0.36
    POSITIVE LOGITS
     shred
    0.35
    Vm
    0.35
     Kag
    0.34
     孔
    0.33
     endoscopic
    0.33
     সাহ
    0.33
    cour
    0.33
     ducks
    0.32
     Virat
    0.32
     Vir
    0.32
    Act Density 0.010%

    No Known Activations