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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @theofarrell99

    present tense verbs ending in "ing".

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @theofarrell99
    New Auto-Interp
    Negative Logits
     solicitation
    1.52
     leasing
    1.49
     хоте
    1.44
     Whittier
    1.44
    req
    1.43
     ثاني
    1.41
     Compensation
    1.41
     Ares
    1.40
     Consultation
    1.40
     consultation
    1.39
    POSITIVE LOGITS
    pher
    0.92
    ↵↵
    0.82
     into
    0.79
     tiến
    0.78
    [.
    0.76
     either
    0.70
    <h3>
    0.69
    [
    0.67
    ↵
    0.67
    あるいは
    0.66
    Act Density 1.762%

    No Known Activations