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

    Neuronpedia

    INDEX
    Explanations

    Golden Globes and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     While
    -1.68
    x
    -1.67
    It
    -1.67
    While
    -1.66
     Despite
    -1.66
    After
    -1.62
     When
    -1.58
     Although
    -1.55
    When
    -1.54
     Since
    -1.53
    POSITIVE LOGITS
     pères
    1.56
     chrétiens
    1.41
    kredit
    1.39
    merksam
    1.38
    cardname
    1.37
    kabel
    1.36
    Answered
    1.36
    ㅁ
    1.34
    Wady
    1.34
     kupa
    1.30
    Act Density 0.010%

    No Known Activations