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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "true" and its variants in the context of code or logical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.71
     témoig
    -0.69
    majánló
    -0.68
    '},
    -0.65
    ########.
    -0.64
    нгред
    -0.64
    cass
    -0.63
     Geſch
    -0.62
    ///
    -0.62
     Geiſt
    -0.60
    POSITIVE LOGITS
     true
    1.71
    true
    1.51
     True
    1.37
    True
    1.34
     TRUE
    1.21
    TRUE
    1.16
     verdadeira
    0.98
     verdadera
    0.94
     verdadero
    0.90
     verdadeiro
    0.89
    Act Density 0.017%

    No Known Activations