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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comma
    0.31
    n
    0.30
     templates
    0.30
     template
    0.28
     transactions
    0.27
     funnel
    0.27
     facilities
    0.26
     conferencing
    0.26
    ν
    0.26
     clip
    0.26
    POSITIVE LOGITS
    otis
    0.36
     beliebt
    0.36
     Prancis
    0.34
     Giá
    0.33
     Vì
    0.32
     Untuk
    0.32
     Namun
    0.32
     خاطر
    0.32
     Meski
    0.32
    yczne
    0.32
    Act Density 0.000%

    No Known Activations