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

    Neuronpedia

    INDEX
    Explanations

    affirm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sesso
    -0.07
     beaucoup
    -0.06
    災
    -0.06
    بود
    -0.06
    .proc
    -0.06
     Arbeit
    -0.06
     sophistication
    -0.06
    oodoo
    -0.06
    -0.06
    isz
    -0.06
    POSITIVE LOGITS
     affirm
    0.12
     affirmed
    0.11
     affirmation
    0.10
     afirm
    0.08
     reaff
    0.08
     утвержд
    0.07
    m
    0.07
     죽
    0.06
    玉
    0.06
    Statements
    0.06
    Act Density 0.005%

    No Known Activations