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

    Neuronpedia

    INDEX
    Explanations

    specifying how to use things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.53
    تين
    0.49
    r
    0.49
    indrome
    0.46
    st
    0.46
    s
    0.45
    னு
    0.43
    os
    0.43
    l
    0.43
    علوم
    0.42
    POSITIVE LOGITS
     DMEM
    0.54
     instead
    0.52
     this
    0.51
     THIS
    0.51
     seçim
    0.49
     proporción
    0.49
     meilleures
    0.48
     tranquila
    0.48
     DELLA
    0.48
    preferably
    0.48
    Act Density 0.040%

    No Known Activations