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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and actions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resonator
    0.54
     成分
    0.53
     bson
    0.52
     testclass
    0.51
     Server
    0.51
    ⊰
    0.50
    ₎
    0.50
    वों
    0.50
     Preprint
    0.50
     Undo
    0.50
    POSITIVE LOGITS
     Col
    0.63
    𝚛
    0.59
     close
    0.58
     fins
    0.58
    Col
    0.57
     fix
    0.57
    ené
    0.57
     कन्न
    0.56
     thinking
    0.55
    કિસ્તા
    0.54
    Act Density 0.000%

    No Known Activations