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

    Neuronpedia

    INDEX
    Explanations

    highly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adro
    -0.08
     ⟨
    -0.07
    bio
    -0.07
     Courtesy
    -0.06
     Stroke
    -0.06
     satisfies
    -0.06
    fixture
    -0.06
     ReturnType
    -0.06
    คล
    -0.06
     punishable
    -0.06
    POSITIVE LOGITS
    )==
    0.07
     gastric
    0.07
    _SOFT
    0.07
    ıyoruz
    0.06
    エ
    0.06
     escri
    0.06
     moist
    0.06
     багат
    0.06
     приня
    0.06
     komt
    0.06
    Act Density 0.014%

    No Known Activations