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

    Neuronpedia

    INDEX
    Explanations

    He wants, it manufactures, scheduled, moved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Las
    0.44
     employs
    0.44
    名为
    0.44
     normalize
    0.43
    Académie
    0.43
    Eugene
    0.42
     classes
    0.41
    Rh
    0.41
     gangster
    0.40
     employ
    0.40
    POSITIVE LOGITS
    \<
    0.58
    \<^
    0.54
    <(
    0.53
    nmid
    0.52
    .=
    0.50
    мін
    0.49
    дил
    0.49
    cents
    0.48
    <.
    0.48
    :<
    0.48
    Act Density 0.000%

    No Known Activations