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

    Neuronpedia

    INDEX
    Explanations

    type returned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     employs
    0.44
    Las
    0.44
    Académie
    0.42
     normalize
    0.42
     classes
    0.42
    Eugene
    0.42
    Rh
    0.42
     employ
    0.41
     memberships
    0.41
    Mil
    0.40
    POSITIVE LOGITS
    \<
    0.52
    <(
    0.50
    <.
    0.47
    \<^
    0.47
    nmid
    0.47
     $<\
    0.47
     \<
    0.47
    cents
    0.46
    стен
    0.46
    :<
    0.46
    Act Density 0.000%

    No Known Activations