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

    Neuronpedia

    INDEX
    Explanations

    counting, recognized, split

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Realistic
    0.84
    =/
    0.76
    ☐
    0.72
    ./
    0.70
    Copyright
    0.68
     realism
    0.67
    }=
    0.67
    りの
    0.67
    ={
    0.66
     realistic
    0.66
    POSITIVE LOGITS
     -*-
    0.93
    split
    0.77
    avises
    0.72
    Split
    0.69
    cher
    0.69
    中学校
    0.69
    airo
    0.68
     split
    0.67
    segu
    0.67
     போல
    0.65
    Act Density 0.000%

    No Known Activations