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

    Neuronpedia

    INDEX
    Explanations

    related kinship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appealed
    0.43
     wielu
    0.43
     amu
    0.42
     Dos
    0.41
     effektiv
    0.41
     combinação
    0.41
     went
    0.40
     upwards
    0.40
     combinación
    0.40
     GoObject
    0.40
    POSITIVE LOGITS
    ற்றும்
    0.37
     سكس
    0.36
    িস্ট
    0.36
    URLConnection
    0.36
    এটি
    0.36
    睥
    0.35
    setUrl
    0.35
     ধারে
    0.35
    갭
    0.35
    িত
    0.34
    Act Density 0.004%

    No Known Activations