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

    Neuronpedia

    INDEX
    Explanations

    fall and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Scholars
    0.44
     Hintergrund
    0.43
     त्याचा
    0.42
     godfather
    0.41
     Carter
    0.41
     Andrew
    0.40
     jeho
    0.40
     Jego
    0.40
     Blue
    0.40
     North
    0.39
    POSITIVE LOGITS
     desgr
    0.46
     damages
    0.43
    жность
    0.42
    ச்சர்
    0.41
    katapos
    0.41
     acidity
    0.41
     máxim
    0.40
     infestations
    0.40
    既然
    0.40
     asymptotics
    0.40
    Act Density 0.005%

    No Known Activations