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

    Neuronpedia

    INDEX
    Explanations

    authenticity, power, and struggle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maximizes
    0.42
     optimize
    0.40
     maximize
    0.40
     বিশেষণ
    0.39
     optimizes
    0.39
     streamlines
    0.38
    듈
    0.38
     increase
    0.38
     helpful
    0.37
     increases
    0.37
    POSITIVE LOGITS
     disillusion
    0.78
     repressed
    0.74
     betrayal
    0.73
     alienation
    0.73
     existential
    0.71
     disillusioned
    0.70
     anxieties
    0.69
     heartbreak
    0.68
     hypocrisy
    0.66
     heroism
    0.66
    Act Density 0.067%

    No Known Activations