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

    Neuronpedia

    INDEX
    Explanations

    alienation, anxiety, fragmentation, disorientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biased
    0.44
    Bias
    0.41
     unfair
    0.41
    cough
    0.41
     bias
    0.40
    꿋
    0.39
    biased
    0.37
     unfairly
    0.37
     persevere
    0.37
    bias
    0.36
    POSITIVE LOGITS
     alienation
    1.02
     atom
    0.95
     nihil
    0.88
     Atom
    0.86
     alienated
    0.85
     spiritual
    0.83
     disen
    0.82
     disorientation
    0.80
     fragmentation
    0.80
     individualism
    0.80
    Act Density 0.029%

    No Known Activations