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

    Neuronpedia

    INDEX
    Explanations

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    both
    0.42
    with
    0.40
     wszystkich
    0.40
     semuanya
    0.38
     všechny
    0.38
    at
    0.37
     lahat
    0.37
    an
    0.36
     všetky
    0.36
    for
    0.35
    POSITIVE LOGITS
     those
    0.45
     theses
    0.44
     них
    0.44
     tenets
    0.44
     failings
    0.43
     hallmarks
    0.42
     bardziej
    0.41
     earliest
    0.40
     thoſe
    0.40
     appellees
    0.40
    Act Density 0.019%

    No Known Activations