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

    Neuronpedia

    INDEX
    Explanations

    imagine or think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Given
    0.89
     conventions
    0.88
    efined
    0.76
    歲
    0.75
    燚
    0.74
     என்பத
    0.72
     Notably
    0.72
     commenced
    0.71
    究竟
    0.71
     అంద
    0.70
    POSITIVE LOGITS
    Think
    1.30
     think
    1.28
     imagine
    1.26
    Imagine
    1.19
     picture
    1.11
     imag
    1.07
    Picture
    1.06
    想象
    1.05
    think
    1.05
     Picture
    1.04
    Act Density 0.243%

    No Known Activations