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

    Neuronpedia

    INDEX
    Explanations

    system structure and breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    w
    0.49
    igkeit
    0.44
    both
    0.44
    BOTH
    0.43
    ik
    0.43
    iss
    0.43
     باشه
    0.42
    oid
    0.42
    ancing
    0.41
    YY
    0.41
    POSITIVE LOGITS
     instancia
    0.56
     organique
    0.56
     instalação
    0.51
     operadores
    0.48
     sistem
    0.47
     sistemas
    0.47
     Builder
    0.47
     formularios
    0.47
     instância
    0.47
     elementi
    0.47
    Act Density 0.009%

    No Known Activations