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

    Neuronpedia

    INDEX
    Explanations

    link separators and subsequent content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Glycer
    0.38
     glycer
    0.38
     WaitFor
    0.38
     mutex
    0.37
     wastage
    0.36
     বিখ্যাত
    0.36
     humus
    0.36
    垛
    0.36
    assapi
    0.35
     InputAction
    0.35
    POSITIVE LOGITS
     federal
    0.49
    federal
    0.46
    聽
    0.42
     federally
    0.41
     ACLU
    0.41
     lawmakers
    0.40
     Senate
    0.39
     NPR
    0.38
     nonprofits
    0.38
    Bloomberg
    0.37
    Act Density 0.015%

    No Known Activations