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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bout
    -0.28
     substitute
    -0.27
    ople
    -0.26
    obel
    -0.25
    obby
    -0.25
     Voice
    -0.25
     substitutes
    -0.25
    åĮº
    -0.24
     title
    -0.24
     Veterans
    -0.24
    POSITIVE LOGITS
    arpa
    0.28
    illes
    0.26
    éĨĽ
    0.26
    æѧè§Ĩ
    0.25
    rens
    0.25
    æ²¥éĿĴ
    0.25
    rale
    0.25
     pháp
    0.24
    个çĻ¾åĪĨ
    0.24
    ALLOW
    0.24
    Act Density 0.541%

    No Known Activations