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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ideal
    -0.07
     nabí
    -0.07
    asi
    -0.07
     energie
    -0.06
     порядке
    -0.06
     gra
    -0.06
     요청
    -0.06
     قرارداد
    -0.06
     �
    -0.06
     शहर
    -0.06
    POSITIVE LOGITS
    ="">
↵
    0.07
    --
↵
    0.07
    $image
    0.06
    "){↵
    0.06
    成
    0.06
    ـــ
    0.06
    学
    0.06
     intercept
    0.06
    ینه
    0.06
     Puppy
    0.06
    Act Density 0.108%

    No Known Activations