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

    Neuronpedia

    INDEX
    Explanations

    feelings of pressure or threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hardcover
    0.78
    olio
    0.77
    риди
    0.72
    exe
    0.72
    噂
    0.68
    oluminescence
    0.68
     क्षार
    0.67
     מש
    0.67
     функции
    0.67
    Problem
    0.66
    POSITIVE LOGITS
     like
    1.42
     compelled
    1.29
     obligated
    1.17
    Like
    1.06
     Like
    1.05
     powerless
    1.01
     empowered
    1.00
     inadequate
    0.98
     obliged
    0.97
     overwhelmed
    0.96
    Act Density 0.224%

    No Known Activations