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

    Neuronpedia

    INDEX
    Explanations

    React `useEffect`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SST
    0.41
    MathClass
    0.39
    reactant
    0.37
     tb
    0.36
    Ttest
    0.36
    tb
    0.36
    烜
    0.35
     пле
    0.35
    Princip
    0.35
    Fel
    0.34
    POSITIVE LOGITS
     past
    0.44
     parade
    0.41
    past
    0.38
     parades
    0.38
    άσ
    0.38
    idescent
    0.38
    maire
    0.37
     once
    0.37
     spé
    0.37
     препара
    0.36
    Act Density 0.001%

    No Known Activations