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

    Neuronpedia

    INDEX
    Explanations

    css/html elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    0.90
    F
    0.87
    K
    0.77
    Ἀ
    0.77
    G
    0.72
    J
    0.72
    و
    0.70
                                
    0.70
                    
    0.69
    Читать
    0.69
    POSITIVE LOGITS
    ется
    0.79
    ку
    0.75
     ఉంది
    0.74
    存于互联网档案馆
    0.74
     nanoparticle
    0.74
     find
    0.73
     possibility
    0.73
     внимание
    0.73
    ет
    0.72
     stanje
    0.72
    Act Density 0.739%

    No Known Activations