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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saddle
    -0.07
     
↵ 
↵
    -0.06
    혁
    -0.06
     mús
    -0.06
     Thánh
    -0.06
    iele
    -0.05
    .pub
    -0.05
     ει
    -0.05
     materiál
    -0.05
     rss
    -0.05
    POSITIVE LOGITS
     applying
    0.08
     SEX
    0.07
     acting
    0.07
     Equal
    0.07
     remedy
    0.07
     disputed
    0.07
    ladık
    0.07
     combined
    0.07
    ROLE
    0.06
     زندگی
    0.06
    Act Density 0.030%

    No Known Activations