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

    Neuronpedia

    INDEX
    Explanations

    risk or reduce negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anabolic
    0.53
     menampilkan
    0.52
     fabulous
    0.48
    нед
    0.46
     neutrophils
    0.46
     Böl
    0.46
     phospholipids
    0.46
     inbuilt
    0.45
    醞
    0.45
     caroten
    0.45
    POSITIVE LOGITS
    on
    0.55
    in
    0.54
    n
    0.50
    <0x82>
    0.47
    гия
    0.46
    et
    0.45
    r
    0.45
    er
    0.45
    at
    0.44
    召
    0.43
    Act Density 0.001%

    No Known Activations