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

    Neuronpedia

    INDEX
    Explanations

    as possible, as needed, as appropriate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Expect
    0.84
     expecting
    0.82
     rely
    0.81
     Requirements
    0.80
     expect
    0.80
     Expect
    0.80
    Expecting
    0.79
    REQUIRE
    0.75
    idyl
    0.75
     expectations
    0.74
    POSITIVE LOGITS
     appropriate
    1.53
     possible
    1.48
     apropri
    1.48
     posible
    1.41
    appropriate
    1.38
     warranted
    1.37
     Appropriate
    1.36
     possibile
    1.32
     möglich
    1.32
    possible
    1.31
    Act Density 0.183%

    No Known Activations