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

    Neuronpedia

    INDEX
    Explanations

    urgent medical and unexpected situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தச
    0.45
    及び
    0.44
    匕
    0.43
     તેમજ
    0.39
    Jahr
    0.39
    Capability
    0.39
    Henry
    0.38
    サラダ
    0.38
     accurately
    0.38
    Radius
    0.37
    POSITIVE LOGITS
     unexpected
    0.78
     urgent
    0.75
     urgently
    0.73
     Unexpected
    0.73
     emergencies
    0.72
     inesper
    0.71
     unexpectedly
    0.70
     unforeseen
    0.70
    unexpected
    0.69
     Urgent
    0.66
    Act Density 0.031%

    No Known Activations