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

    Neuronpedia

    INDEX
    Explanations

    commands and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.61
    y
    0.54
    z
    0.53
    x
    0.52
    ging
    0.52
    ks
    0.51
    '
    0.51
    kk
    0.49
    ling
    0.49
    ATION
    0.49
    POSITIVE LOGITS
    getVisibility
    0.48
    았
    0.46
    بار
    0.44
    ，
    0.44
    א
    0.43
    SpacerItem
    0.42
    Vaterpolo
    0.41
    த்து
    0.40
    Baer
    0.40
    SearchBar
    0.40
    Act Density 0.425%

    No Known Activations