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

    Neuronpedia

    INDEX
    Explanations

    compound modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     answered
    0.44
    回答
    0.42
    |_
    0.40
     vidéos
    0.39
     ihren
    0.39
     ตอบ
    0.39
     منص
    0.39
     monomials
    0.37
     алма
    0.37
     exclusives
    0.36
    POSITIVE LOGITS
    beginPath
    0.37
     animali
    0.37
     animais
    0.37
     yarat
    0.37
     बुखार
    0.35
    盛
    0.34
     posición
    0.34
     শ্বাস
    0.34
     sophisticated
    0.33
     commissioner
    0.33
    Act Density 0.003%

    No Known Activations