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

    Neuronpedia

    INDEX
    Explanations

    concepts and society

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Approach
    0.68
    Ruby
    0.67
     Ruby
    0.66
     Pestic
    0.66
    Pizza
    0.65
    Trash
    0.64
    Gaming
    0.63
    Rails
    0.61
    Dual
    0.61
     Orchid
    0.61
    POSITIVE LOGITS
     causation
    0.90
     itself
    0.86
     stereotypes
    0.85
    iness
    0.83
    annuation
    0.81
     societies
    0.79
     regimes
    0.76
     stereotyp
    0.74
     NGOs
    0.74
    goers
    0.74
    Act Density 0.746%

    No Known Activations