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

    Neuronpedia

    INDEX
    Explanations

    hit or press an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    -1.51
    when
    -1.47
    because
    -1.44
    /"
    -1.43
    </h3>
    -1.41
    5
    -1.39
    不仅
    -1.36
    Usted
    -1.30
    Alguien
    -1.30
     esos
    -1.29
    POSITIVE LOGITS
     to
    1.52
    ︲
    1.48
    logique
    1.34
     ardından
    1.34
    РЯ
    1.33
     poème
    1.30
    ЦА
    1.29
    %%%%%%%%%%
    1.29
     eliminare
    1.29
     Alguns
    1.27
    Act Density 0.030%

    No Known Activations