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

    Neuronpedia

    INDEX
    Explanations

    necessity to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MUST
    0.54
    MUST
    0.52
     harus
    0.52
     somehow
    0.51
     know
    0.50
     phải
    0.49
    必须要
    0.48
    ต้อง
    0.48
     understand
    0.47
     HAVE
    0.47
    POSITIVE LOGITS
     unexpectedly
    0.54
     fight
    0.52
     hunt
    0.50
     struggle
    0.46
     scramble
    0.46
    簡単な
    0.45
     exert
    0.44
     reminders
    0.44
     unnecessarily
    0.44
     unusually
    0.44
    Act Density 0.011%

    No Known Activations