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

    Neuronpedia

    INDEX
    Explanations

    states, actions, and problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     archivo
    0.50
     manipulation
    0.48
     drept
    0.47
     abusive
    0.47
     illusions
    0.46
     mardi
    0.46
     देओल
    0.46
     genom
    0.45
     lundi
    0.45
     neuf
    0.45
    POSITIVE LOGITS
    Capacity
    0.43
    years
    0.41
    Increase
    0.40
    ור
    0.40
    Added
    0.39
     уг
    0.38
    Growth
    0.38
    Started
    0.38
    topics
    0.38
    Impact
    0.38
    Act Density 0.005%

    No Known Activations