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

    Neuronpedia

    INDEX
    Explanations

    ative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Phen
    -0.08
     astonishing
    -0.08
    Exclusive
    -0.08
     이야기
    -0.08
     imaginable
    -0.08
    Detector
    -0.08
     relentless
    -0.07
     محیط
    -0.07
    REMOTE
    -0.07
     درمیان
    -0.07
    POSITIVE LOGITS
     purposes
    0.10
     amaç
    0.09
    目的
    0.09
     Cath
    0.08
     doeleinden
    0.08
    徽
    0.08
     amacı
    0.08
    用途
    0.08
    域
    0.08
     목적
    0.08
    Act Density 0.013%

    No Known Activations