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

    Neuronpedia

    INDEX
    Explanations

    different contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    When
    0.57
    Genetic
    0.57
    We
    0.57
    Which
    0.54
    If
    0.51
    Las
    0.50
    Wenn
    0.50
    And
    0.49
    Growing
    0.49
    It
    0.49
    POSITIVE LOGITS
     guardian
    0.52
     condiment
    0.50
     fiance
    0.49
     municipality
    0.48
     mastermind
    0.48
     heavyweight
    0.47
     citadel
    0.47
     poth
    0.46
    ዴ
    0.46
     pund
    0.46
    Act Density 0.005%

    No Known Activations