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

    Neuronpedia

    INDEX
    Explanations

    things increase

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magically
    0.62
     للصف
    0.60
    כר
    0.59
    VIEWS
    0.59
     CRED
    0.58
    这样一个
    0.56
    quefois
    0.55
    CLUS
    0.55
    jsce
    0.55
    ського
    0.54
    POSITIVE LOGITS
     sehr
    0.66
     expenditure
    0.60
     rises
    0.60
     Huber
    0.59
     biliary
    0.58
     requires
    0.57
     arises
    0.57
    !.
    0.57
     disassembly
    0.57
     trastornos
    0.56
    Act Density 0.000%

    No Known Activations