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

    Neuronpedia

    INDEX
    Explanations

    emergency preparedness and safety plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dop
    0.41
     Pont
    0.39
     آف
    0.38
     nac
    0.37
    চা
    0.37
     grafting
    0.37
     Phyt
    0.37
     Dich
    0.36
     modulation
    0.36
     sympat
    0.36
    POSITIVE LOGITS
    plans
    0.70
    Emergency
    0.68
    Plans
    0.67
    emergency
    0.67
     plans
    0.66
    plan
    0.66
     emergency
    0.65
     plan
    0.65
    Escape
    0.64
     preparedness
    0.63
    Act Density 0.009%

    No Known Activations