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

    Neuronpedia

    INDEX
    Explanations

    drifting, fading, pretending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    😈
    0.43
     unorthodox
    0.42
     வில்
    0.40
     unconventional
    0.40
     Transform
    0.39
     horrendous
    0.39
     risky
    0.38
    binomial
    0.38
     Transforms
    0.37
    Rv
    0.37
    POSITIVE LOGITS
     flound
    0.89
     drifting
    0.86
     shuffling
    0.85
     adrift
    0.80
     flounder
    0.80
    漂
    0.79
     grasping
    0.78
     grop
    0.76
     drift
    0.75
     shuffle
    0.73
    Act Density 0.041%

    No Known Activations