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

    Neuronpedia

    INDEX
    Explanations

    help followed by argument descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ("",
    0.47
     '',
    0.41
     $("
    0.41
     “,
    0.40
     ”,
    0.39
     Shreve
    0.39
    ("\"
    0.39
     \"
    0.38
     !,
    0.38
     …,
    0.37
    POSITIVE LOGITS
    ळं
    0.40
    &)
    0.39
     commande
    0.39
    ='')
    0.37
     OG
    0.37
     označ
    0.36
     নামকরণ
    0.36
    ью
    0.36
    Visibility
    0.35
    γμα
    0.35
    Act Density 0.006%

    No Known Activations