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

    Neuronpedia

    INDEX
    Explanations

    text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Any
    -0.08
     Placeholder
    -0.08
    .BAD
    -0.07
    ഭ
    -0.07
     positif
    -0.07
    ession
    -0.07
     eventuele
    -0.07
    ensitivity
    -0.07
    કારી
    -0.07
     perfeitamente
    -0.07
    POSITIVE LOGITS
     vielmehr
    0.10
     plutôt
    0.09
     clan
    0.08
     profitable
    0.08
     masu
    0.08
     visions
    0.08
     उससे
    0.08
     cherish
    0.08
    تل
    0.08
     أر
    0.08
    Act Density 0.046%

    No Known Activations