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

    Neuronpedia

    INDEX
    Explanations

    potential negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tragedy
    1.06
     tragic
    1.00
     heartbreaking
    0.91
     horrific
    0.88
     deadly
    0.88
     horrifying
    0.85
     fatalities
    0.84
     crisis
    0.84
     failure
    0.84
     Tragedy
    0.84
    POSITIVE LOGITS
     Risks
    0.92
     βοη
    0.92
    Ris
    0.90
     stimulates
    0.89
     ISI
    0.87
     Ris
    0.85
     risks
    0.84
    带来
    0.83
    potential
    0.83
    Potential
    0.83
    Act Density 0.545%

    No Known Activations