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

    Neuronpedia

    INDEX
    Explanations

    when or until clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Although
    0.52
    While
    0.50
    Since
    0.49
    Dengan
    0.48
    Because
    0.47
    Selain
    0.47
    When
    0.46
    Menurut
    0.46
    Namun
    0.46
    What
    0.45
    POSITIVE LOGITS
     they
    0.77
     we
    0.67
     she
    0.66
     he
    0.62
     there
    0.60
     warranted
    0.55
     triggered
    0.55
     someone
    0.52
     prompted
    0.51
     signaled
    0.51
    Act Density 0.344%

    No Known Activations