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

    Neuronpedia

    INDEX
    Explanations

    resonates with personal experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outcomes
    0.43
     Outcome
    0.41
     outcome
    0.40
    Outcome
    0.39
     руками
    0.39
     Recap
    0.38
    communicate
    0.38
    ARN
    0.38
     Outcomes
    0.37
    聚焦
    0.37
    POSITIVE LOGITS
     personally
    0.65
     resonance
    0.63
     strongest
    0.62
     resonate
    0.61
     strangely
    0.59
     deeply
    0.59
     vis
    0.59
     inexplic
    0.59
     resonates
    0.59
     strongly
    0.58
    Act Density 0.013%

    No Known Activations