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

    Neuronpedia

    INDEX
    Explanations

    end of a process or cycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     począ
    0.48
    Skip
    0.43
     başta
    0.41
     اولیه
    0.41
    Tk
    0.41
     Throughout
    0.41
     bruker
    0.41
     throughout
    0.40
    ប្រើ
    0.40
     ranging
    0.39
    POSITIVE LOGITS
     abruptly
    0.66
     satisfactorily
    0.64
     exhausted
    0.59
     exhaustion
    0.59
     triumphant
    0.59
     satisfactor
    0.58
     gracefully
    0.57
     peacefully
    0.57
     abrupt
    0.56
    🔚
    0.55
    Act Density 0.015%

    No Known Activations