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

    Neuronpedia

    INDEX
    Explanations

    model for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HZ
    0.45
    AKS
    0.41
    IMPLEMENT
    0.37
    Autonomous
    0.37
    INTRO
    0.37
    ầ
    0.37
     xong
    0.37
    xcuserdatad
    0.36
    SUN
    0.36
    $}}
    0.36
    POSITIVE LOGITS
     estimates
    0.39
     anecdotal
    0.39
    ടുന്ന
    0.39
    ší
    0.39
     espl
    0.39
    oit
    0.38
     gris
    0.38
     restful
    0.37
     si
    0.37
     k
    0.36
    Act Density 0.002%

    No Known Activations