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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     needed
    -0.07
    썬
    -0.07
    .Handler
    -0.07
     Utah
    -0.07
    עס
    -0.06
    notation
    -0.06
    拿了
    -0.06
    استعمال
    -0.06
    넌
    -0.06
     arou
    -0.06
    POSITIVE LOGITS
     ?>
↵
↵
    0.08
    魉
    0.07
    申し
    0.07
     latin
    0.07
    -spec
    0.07
    >
↵
    0.07
     Strap
    0.07
     hari
    0.07
    -Class
    0.07
    aces
    0.07
    Act Density 0.043%

    No Known Activations