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

    Neuronpedia

    INDEX
    Explanations

    if applicable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    followlike
    0.52
    rict
    0.47
    }]$,
    0.46
    moid
    0.45
    basan
    0.44
    harth
    0.44
     इश
    0.43
    सुम
    0.43
    counterx
    0.43
     Pounds
    0.43
    POSITIVE LOGITS
    Entrepreneur
    0.46
    Artist
    0.45
     Erste
    0.45
    Legend
    0.45
    тации
    0.44
    Est
    0.43
    Adresse
    0.43
     ontvang
    0.43
    Er
    0.42
     rozwiąz
    0.41
    Act Density 0.001%

    No Known Activations