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

    Neuronpedia

    INDEX
    Explanations

    range, you, temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    timedelta
    0.57
    oretical
    0.54
    subdirectory
    0.54
    sectors
    0.54
    bestroute
    0.52
    mobile
    0.51
    ousands
    0.49
    raining
    0.49
     philanthropist
    0.49
    students
    0.49
    POSITIVE LOGITS
     For
    0.55
     Você
    0.51
     Select
    0.49
     Drama
    0.48
     You
    0.48
     você
    0.47
     Think
    0.46
     A
    0.45
     Sel
    0.45
    R
    0.45
    Act Density 0.005%

    No Known Activations