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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deletes
    -0.06
     detriment
    -0.06
     aslında
    -0.06
     Dest
    -0.06
    のお
    -0.06
    argo
    -0.06
    apGestureRecognizer
    -0.06
     pissed
    -0.06
    reverse
    -0.06
     rubbed
    -0.06
    POSITIVE LOGITS
    orrect
    0.07
    _hdr
    0.07
    reshold
    0.06
    :::::::::::
    0.06
    ้าส
    0.06
    qx
    0.06
     Corp
    0.06
     Vice
    0.06
    busters
    0.06
    ationally
    0.06
    Act Density 0.006%

    No Known Activations