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

    Neuronpedia

    INDEX
    Explanations

    defines roles and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Debugger
    0.47
    arnell
    0.45
    quist
    0.44
     يش
    0.44
    üd
    0.44
    estre
    0.44
    gb
    0.42
     ليب
    0.42
     قوي
    0.41
    술
    0.41
    POSITIVE LOGITS
    しの
    0.54
     inanimate
    0.49
    スピード
    0.48
     Shap
    0.47
     nascost
    0.46
    体の
    0.45
     inertia
    0.45
     Luca
    0.44
     protég
    0.44
     bragging
    0.44
    Act Density 0.001%

    No Known Activations